You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/08/08 15:27:34 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@b4e36c61fcf07e3e75649e72bd97a35603edc2b6)
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 3797685af deploying docs (apache/tvm@b4e36c61fcf07e3e75649e72bd97a35603edc2b6)
3797685af is described below
commit 3797685af87a716e2dd1133b67208b0f4d87d0f2
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Aug 8 15:27:26 2022 +0000
deploying docs (apache/tvm@b4e36c61fcf07e3e75649e72bd97a35603edc2b6)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1791 ++++++++++----------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 107 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 10 +-
.../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 | 14 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 42 +-
docs/commit_hash | 2 +-
docs/genindex.html | 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 | 14 +-
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 | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 19 +-
docs/how_to/deploy_models/deploy_prequantized.html | 7 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1791 ++++++++++----------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 107 +-
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/objects.inv | Bin 23018 -> 23027 bytes
docs/reference/api/doxygen/builtin_8h.html | 3 +
docs/reference/api/doxygen/builtin_8h_source.html | 31 +-
.../api/doxygen/data__layout_8h_source.html | 3 +-
.../api/doxygen/namespacemembers_func_p.html | 6 +-
.../api/doxygen/namespacemembers_func_r.html | 5 +-
.../api/doxygen/namespacemembers_func_s.html | 6 +-
.../api/doxygen/namespacemembers_func_u.html | 5 +-
docs/reference/api/doxygen/namespacemembers_p.html | 6 +-
docs/reference/api/doxygen/namespacemembers_r.html | 5 +-
docs/reference/api/doxygen/namespacemembers_s.html | 8 +-
docs/reference/api/doxygen/namespacemembers_u.html | 5 +-
.../namespacetvm_1_1relay_1_1transform.html | 22 +
.../doxygen/namespacetvm_1_1tir_1_1builtin.html | 23 +
.../reference/api/doxygen/relay_2transform_8h.html | 3 +
.../api/doxygen/relay_2transform_8h_source.html | 3 +-
docs/reference/api/doxygen/search/all_11.js | 2 +-
docs/reference/api/doxygen/search/all_13.js | 1 +
docs/reference/api/doxygen/search/all_14.js | 4 +-
docs/reference/api/doxygen/search/all_16.js | 2 +-
docs/reference/api/doxygen/search/functions_10.js | 2 +-
docs/reference/api/doxygen/search/functions_12.js | 1 +
docs/reference/api/doxygen/search/functions_13.js | 2 +-
docs/reference/api/doxygen/search/functions_15.js | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/tir.html | 49 +-
.../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 | 6 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 34 +-
docs/tutorial/tensor_expr_get_started.html | 42 +-
148 files changed, 2923 insertions(+), 2684 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 a6e4c6c3f..75db1d275 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 0.894 seconds)
+ **Total running time of the script:** ( 1 minutes 3.333 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 7117eeefb..138cbfa46 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.zipbe3d274f-1a78-4877-be83-f3137dc20d92 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip3b21b8e4-f5d5-4fc9-bbad-d7f754b399dd 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 81928f7d8..beb861070 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, 60.6MB/s]
29%|##9 | 12.1M/41.5M [00:00<00:00, 52.8MB/s]
41%|####1 | 17.2M/41.5M [00:00<00:00, 45.1MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 47.6MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 47.4MB/s]
94%|#########3| 39.0M/41.5M [00:00<00:00, 54.1MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 49.6MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 36.4MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 34.1MB/s]
53%|#####2 | 21.9M/41.5M [00:00<00:00, 46.9MB/s]
65%|######5 | 27.2M/41.5M [00:00<00:00, 33.6MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 33.1MB/s]
86%|########5 | 35.6M/41.5M [00:01<00:00, 32.9MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 37.1MB/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 2381f390c..de36743a4 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]
11%|#1 | 4.93M/44.7M [00:00<00:00, 51.7MB/s]
22%|##2 | 9.86M/44.7M [00:00<00:00, 49.4MB/s]
67%|######7 | 30.1M/44.7M [00:00<00:00, 122MB/s]
94%|#########3| 41.9M/44.7M [00:00<00:00, 102MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 95.6MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
50%|##### | 22.4M/44.7M [00:00<00:00, 235MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 255MB/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 785f16bfc..a844ff1a3 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 0.570 seconds)
+ **Total running time of the script:** ( 1 minutes 6.013 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 6d3e73fe2..19fff2471 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**04:54.167** total execution time for **how_to_compile_models** files:
+**05:11.018** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:00.894 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:06.013 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:00.570 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.333 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.925 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.701 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.202 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.167 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.396 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.821 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.311 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.985 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.427 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:23.366 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.187 | 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_keras.py` (``from_keras.py``) | 00:15.024 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.262 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.421 | 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 11857c193..84fd2cb8b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.5677 15.5340 15.7678 15.4708 0.0899
+ 15.7922 15.7958 16.0043 15.6177 0.1204
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 921d628bc..996147fb0 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]
2%|1 | 3.26M/170M [00:00<00:05, 33.4MB/s]
4%|3 | 6.45M/170M [00:00<00:05, 32.1MB/s]
19%|#8 | 31.9M/170M [00:00<00:01, 137MB/s]
34%|###3 | 57.4M/170M [00:00<00:00, 178MB/s]
49%|####9 | 84.0M/170M [00:00<00:00, 213MB/s]
64%|######4 | 110M/170M [00:00<00:00, 231MB/s]
79%|#######9 | 135M/170M [00:00<00:00, 242MB/s]
94%|#########4| 160M/170M [00:00<00:00, 250MB/s]
100%|##########| 170M/170M [00:00<00:00, 207MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
10%|# | 17.5M/170M [00:00<00:00, 184MB/s]
24%|##4 | 41.5M/170M [00:00<00:00, 224MB/s]
39%|###8 | 65.6M/170M [00:00<00:00, 237MB/s]
52%|#####2 | 88.9M/170M [00:00<00:00, 240MB/s]
66%|######6 | 113M/170M [00:00<00:00, 244MB/s]
80%|######## | 136M/170M [00:00<00:00, 242MB/s]
94%|#########3| 160M/170M [00:00<00:00, 244MB/s]
100%|##########| 170M/170M [00:00<00:00, 239MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 53.356 seconds)
+ **Total running time of the script:** ( 2 minutes 57.376 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 0d7ad2a54..d2fd5ebf8 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]
85%|########5 | 11.6M/13.6M [00:00<00:00, 116MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 124MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 173MB/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)
- 90.1342 90.0681 92.7173 89.8600 0.3264
+ 90.3919 90.1951 102.9096 90.0938 1.3306
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.811 seconds)
+ **Total running time of the script:** ( 1 minutes 8.733 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 2de65ac52..85e8f132c 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)
- 118.2781 118.3908 120.2176 116.5204 0.7695
+ 120.3294 120.2923 121.7232 119.4218 0.3800
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 57.365 seconds)
+ **Total running time of the script:** ( 2 minutes 2.396 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 dedff553a..ca1843b08 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 16.287 seconds)
+ **Total running time of the script:** ( 1 minutes 29.418 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 1aa5d6272..aaf115afd 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]
5%|5 | 6654/132723 [00:00<00:01, 66531.81KB/s]
11%|#1 | 14815/132723 [00:00<00:01, 75398.60KB/s]
17%|#7 | 22834/132723 [00:00<00:01, 77584.37KB/s]
23%|##3 | 30891/132723 [00:00<00:01, 78756.00KB/s]
30%|##9 | 39190/132723 [00:00<00:01, 80058.14KB/s]
36%|###5 | 47273/132723 [00:00<00:01, 80316.85KB/s]
42%|####1 | 55454/132723 [00:00<00:00, 80801.86KB/s]
48%|####7 | 63595/132723 [00:00<00:00, 80993.47KB/s]
54%|#####4 | 71708/132723 [00:00<00:00, 81035.06KB/s]
60%|###### | 79874/132723 [00:01<00:00, 81225.18KB/s]
66%|######6 | 88018/132723 [00:01<00:00, 81288.02KB/s]
72%|#######2 | 96180/132723 [00:01<00:00, 81387.59KB/s]
79%|#######8 | 104319/132723 [00:01<00:00, 80967.09KB/s]
85%|########4 | 112431/132723 [00:01<00:00, 81010.63KB/s]
91%|#########1| 120841/132723 [00:01<00:00, 81935.72KB/s]
97%|########
#7| 129131/132723 [00:01<00:00, 82224.03KB/s]
100%|##########| 132723/132723 [00:01<00:00, 79923.31KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6621/132723 [00:00<00:01, 66206.43KB/s]
11%|#1 | 15039/132723 [00:00<00:01, 76773.97KB/s]
18%|#7 | 23502/132723 [00:00<00:01, 80358.44KB/s]
24%|##4 | 31938/132723 [00:00<00:01, 81935.86KB/s]
30%|### | 40434/132723 [00:00<00:01, 83024.43KB/s]
37%|###6 | 48895/132723 [00:00<00:01, 83561.29KB/s]
43%|####3 | 57407/132723 [00:00<00:00, 84069.17KB/s]
50%|####9 | 65948/132723 [00:00<00:00, 84494.56KB/s]
56%|#####6 | 74447/132723 [00:00<00:00, 84647.31KB/s]
62%|######2 | 82941/132723 [00:01<00:00, 84734.39KB/s]
69%|######8 | 91438/132723 [00:01<00:00, 84803.30KB/s]
75%|#######5 | 99933/132723 [00:01<00:00, 84842.53KB/s]
82%|########1 | 108418/132723 [00:01<00:00, 84808.68KB/s]
88%|########8 | 116899/132723 [00:01<00:00, 67411.23KB/s]
94%|#########4| 125344/132723 [00:01<00:00, 71759.77KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 79166.68KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 32.501 seconds)
+ **Total running time of the script:** ( 2 minutes 34.566 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 b75dd379d..d1fc327bd 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:00.673** total execution time for **how_to_deploy_models** files:
+**11:27.444** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:53.356 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:57.376 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:32.501 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:34.566 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:57.365 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:02.396 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:16.287 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:29.418 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.811 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.733 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.645 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.625 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.480 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.870 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.222 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.454 | 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 e4f4d9155..1f79932a5 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.zipf00b1f96-5da5-44c2-b4b4-2f21a2c4276c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip0a9d853e-d3fb-4715-bcc5-659765878364 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 cb0ac6e58..ff4da10f1 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
=================
-**00:40.297** total execution time for **how_to_extend_tvm** files:
+**00:40.836** 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``) | 00:36.898 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.682 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.440 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.208 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.951 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.937 | 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 93e658634..fcce2caef 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: 9820us [9820us] (44.78%; 44.78%)
- FoldScaleAxis: 12108us [12us] (55.22%; 55.22%)
- FoldConstant: 12097us [2046us] (55.16%; 99.90%)
- InferType: 10050us [10050us] (45.83%; 83.08%)
+ InferType: 6544us [6544us] (45.34%; 45.34%)
+ FoldScaleAxis: 7888us [7us] (54.66%; 54.66%)
+ FoldConstant: 7881us [1614us] (54.61%; 99.92%)
+ InferType: 6268us [6268us] (43.43%; 79.52%)
@@ -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: 9513us [9513us] (44.85%; 44.85%)
- FoldScaleAxis: 11698us [10us] (55.15%; 55.15%)
- FoldConstant: 11688us [2288us] (55.10%; 99.91%)
- InferType: 9400us [9400us] (44.31%; 80.42%)
+ InferType: 6298us [6298us] (44.82%; 44.82%)
+ FoldScaleAxis: 7753us [5us] (55.18%; 55.18%)
+ FoldConstant: 7748us [1639us] (55.14%; 99.94%)
+ InferType: 6109us [6109us] (43.48%; 78.85%)
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 60e0b6219..a0fa9f9d7 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 50.286589 ms
+ Convolution: 37.907445 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 e6d547d5c..b18cd2af3 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.002721 ms
+ conv2d with tensor core: 7.297706 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 c42a34aef..77ef8bbae 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: 0.018111
- Baseline: 3.311390
+ Numpy running time: 0.018634
+ Baseline: 3.290959
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.295603
+ Opt1: 0.296151
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.333779
+ Opt2: 0.336130
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114166
+ Opt3: 0.118537
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110476
+ Opt4: 0.111252
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111631
+ Opt5: 0.111293
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.144850
+ Opt6: 0.145257
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 ed1c4330a..4d21f6125 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
=================
-**00:34.003** total execution time for **how_to_optimize_operators** files:
+**00:34.097** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.770 | 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``) | 00:01.229 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.239 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.004 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.012 | 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 795b404d2..829a368d3 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
=================
-**05:57.842** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:15.999** 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``) | 03:12.949 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:28.171 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.035 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:24.008 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.184 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.414 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.479 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.644 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.642 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.903 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.552 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.859 | 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 b74c2001e..04f735cde 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
@@ -240,483 +240,476 @@ 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" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [392]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [256]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
- 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[14] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[15] = 0f32
for (rc.outer.outer: int32, 0, 64) {
for (ry.outer.outer: int32, 0, 3) {
let cse_var_2: int32 = (rc.outer.outer*72)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [392], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 90)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 188)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 286)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [256], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 8)*9)) + cse_var_1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 98), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 2), 8)*9)) + cse_var_1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 60), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 8)*9)) + cse_var_1)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 128)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 160)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 192)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 224)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 136)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 168)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 200)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 232)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 97)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 129)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 161)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 193)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 137)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 169)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 201)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 233)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 98)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 130)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 162)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 194)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 226)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 170)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 202)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 234)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 131)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 163)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 195)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 227)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 139)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 203)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 235)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 100)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 132)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 164)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 196)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 140)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 172)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 204)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 236)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 101)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 133)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 165)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 197)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 229)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 173)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 205)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 237)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 134)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 166)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 198)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 230)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 142)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 174)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 206)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 238)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 103)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 135)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 167)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 199)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 143)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 175)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 207)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 239)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 91)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 189)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 287)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 8)*9)) + cse_var_1) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 98), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 2), 8)*9)) + cse_var_1) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 60), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 8)*9)) + cse_var_1) + 1)]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 128)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 160)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 192)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 224)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 136)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 168)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 200)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 232)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 97)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 129)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 161)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 193)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 137)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 169)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 201)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 233)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 98)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 130)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 162)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 194)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 226)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 170)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 202)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 234)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 131)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 163)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 195)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 227)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 139)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 203)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 235)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 100)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 132)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 164)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 196)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 140)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 172)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 204)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 236)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 101)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 133)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 165)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 197)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 229)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 173)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 205)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 237)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 134)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 166)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 198)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 230)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 142)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 174)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 206)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 238)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 103)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 135)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 167)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 199)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 143)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 175)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 207)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 239)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 92)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 190)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 288)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 8)*9)) + cse_var_1) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 98), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 2), 8)*9)) + cse_var_1) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 60), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 8)*9)) + cse_var_1) + 2)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 128)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 160)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 192)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 224)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 136)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 168)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 200)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 232)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 97)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 129)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 161)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 193)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 137)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 169)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 201)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 233)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 98)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 130)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 162)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 194)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 226)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 170)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 202)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 234)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 131)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 163)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 195)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 227)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 139)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 203)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 235)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 100)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 132)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 164)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 196)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 140)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 172)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 204)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 236)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 101)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 133)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 165)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 197)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 229)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 173)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 205)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 237)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 134)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 166)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 198)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 230)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 142)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 174)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 206)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 238)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 103)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 135)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 167)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 199)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 143)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 175)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 207)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 239)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 196)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 4)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 588)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 12)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 16)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 980)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 20)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1176)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 24)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1372)] = max((conv2d_nchw_1[(i1.inner + 14)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 28)]), 0f32)
}
}
}
@@ -771,7 +764,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.371 ms
+ Execution time of this operator: 0.321 ms
@@ -819,36 +812,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=8)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=8)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -868,12 +861,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ 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=98)
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=4)
+ 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=64)
+ 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=98)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -893,430 +886,456 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[16];
+ __shared__ float pad_temp_shared[392];
+ __shared__ float kernel_shared[256];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- 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[14] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 90)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 188)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 286)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) & 7) * 9)) + (ry_outer_outer * 3))];
+ if (((int)threadIdx.x) < 60) {
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 4) & 7) * 9)) + (ry_outer_outer * 3))];
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 128)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 160)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 192)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 224)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 168)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 200)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 232)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 129)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 161)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 193)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 169)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 201)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 233)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 130)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 162)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 194)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 226)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 170)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 202)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 234)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 131)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 163)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 195)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 227)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 203)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 235)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 132)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 164)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 196)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 172)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 204)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 236)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 133)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 165)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 197)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 229)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 173)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 205)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 237)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 134)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 166)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 198)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 230)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 174)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 206)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 238)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 103)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 135)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 167)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 199)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 175)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 207)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 239)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 91)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 189)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 287)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
+ if (((int)threadIdx.x) < 60) {
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 4) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 128)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 160)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 192)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 224)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 168)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 200)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 232)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 129)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 161)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 193)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 169)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 201)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 233)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 130)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 162)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 194)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 226)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 170)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 202)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 234)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 131)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 163)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 195)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 227)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 203)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 235)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 132)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 164)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 196)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 172)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 204)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 236)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 133)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 165)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 197)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 229)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 173)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 205)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 237)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 134)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 166)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 198)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 230)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 174)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 206)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 238)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 103)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 135)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 167)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 199)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 175)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 207)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 239)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 92)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 190)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 288)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
+ if (((int)threadIdx.x) < 60) {
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 4) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 128)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 160)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 192)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 224)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 168)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 200)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 232)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 129)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 161)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 193)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 169)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 201)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 233)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 130)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 162)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 194)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 226)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 170)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 202)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 234)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 131)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 163)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 195)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 227)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 203)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 235)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 132)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 164)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 196)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 172)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 204)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 236)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 133)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 165)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 197)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 229)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 173)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 205)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 237)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 134)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 166)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 198)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 230)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 174)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 206)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 238)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 103)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 135)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 167)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 199)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 175)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 207)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 239)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 196)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 4)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 588)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 12)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 8)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 980)] = max((conv2d_nchw[(i1_inner + 10)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 20)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1176)] = max((conv2d_nchw[(i1_inner + 12)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 24)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1372)] = max((conv2d_nchw[(i1_inner + 14)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 28)]), 0.000000e+00f);
}
}
@@ -1378,7 +1397,7 @@ 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 12.949 seconds)
+ **Total running time of the script:** ( 3 minutes 28.171 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 214c2f72e..df9a3fd53 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)
- 10.0574 10.0510 10.1011 10.0202 0.0333
+ 9.8635 9.8866 9.8979 9.8059 0.0410
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 8c78d1888..122f570f7 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)
- 754.1807 753.9919 755.3020 753.2483 0.8490
+ 760.4743 760.4410 760.8218 760.1602 0.2711
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.035 seconds)
+ **Total running time of the script:** ( 1 minutes 24.008 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 fb5984df2..d403cc131 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
@@ -397,30 +397,103 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
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, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
+ {
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 16) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
+ for (i.inner: int32, 0, 32) {
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_2: int32 = ((i.outer.inner*512) + (i.inner*16))
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_4: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+ compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -476,7 +549,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.505 ms
+ Execution time of this operator: 1.705 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 e2495275a..fecb4af19 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:45.688** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.154** 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``) | 00:45.653 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.120 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 a7984c0fe..b154bcfcc 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: 175.24/175.24 result: MeasureResult(costs=(0.0013210377111111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.035792112350464, timestamp=1659740547.466681) [('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: 0.00/175.24 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 203.60/203.60 result: MeasureResult(costs=(0.001137045511111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0944693088531494, timestamp=1659968293.8274136) [('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: 0.00/203.60 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: 259.84/259.84 result: MeasureResult(costs=(0.0008909375966850829,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4841654300689697, timestamp=1659740548.388527) [('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: 0.00/259.84 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.06/260.06 result: MeasureResult(costs=(0.0008901913093922652,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.786071538925171, timestamp=1659968294.7591627) [('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: 0.00/260.06 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: 0.00/259.84 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.06 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: 0.00/259.84 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.06 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: 5.45/259.84 result: MeasureResult(costs=(0.042476408,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.842756748199463, timestamp=1659740552.940398) [('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: 3.34/259.84 result: MeasureResult(costs=(0.06939392125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.545986652374268, timestamp=1659740554.176307) [('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: 0.00/259.84 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.29/260.06 result: MeasureResult(costs=(0.04377531925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8445255756378174, timestamp=1659968299.3311553) [('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: 3.34/260.06 result: MeasureResult(costs=(0.06939442074999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.597178220748901, timestamp=1659968300.5865803) [('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: 0.00/260.06 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: 25.97/259.84 result: MeasureResult(costs=(0.008912814833333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1480615139007568, timestamp=1659740565.1115236) [('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: 0.00/259.84 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 27.09/260.06 result: MeasureResult(costs=(0.008544821499999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3186297416687012, timestamp=1659968311.6763117) [('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: 0.00/260.06 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: 0.00/259.84 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.06 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: 0.001219
+ Time cost of this operator: 0.001217
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 8d25eae95..c20228842 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 311.0 98.725 (1, 2, 10, 10, 3) 2 1 [311.0]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.026 0.961 (1, 6, 10, 10) 1 1 [3.026]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.991 0.315 (1, 1, 10, 10, 3) 1 1 [0.991]
- Total_time - 315.017 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.713 (1, 2, 10, 10, 3) 2 1 [310.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.071 0.977 (1, 6, 10, 10) 1 1 [3.071]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.975 0.31 (1, 1, 10, 10, 3) 1 1 [0.975]
+ Total_time - 314.346 - - - - -
@@ -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 90.312 97.058 (1, 6, 10, 10, 1) 2 1 [90.312]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.784 1.917 (1, 6, 10, 10) 1 1 [1.784]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 1.025 (1, 1, 10, 10, 3) 1 1 [0.954]
- Total_time - 93.05 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 118.4 97.711 (1, 6, 10, 10, 1) 2 1 [118.4]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.82 1.502 (1, 6, 10, 10) 1 1 [1.82]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.787 (1, 1, 10, 10, 3) 1 1 [0.954]
+ Total_time - 121.174 - - - - -
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 093fb9bda..c5d067d86 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/tmptdcmv1sf/images/random'
+ '/tmp/tmp6nerfeb0/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmptdcmv1sf/images/target contains 8144 images
- /tmp/tmptdcmv1sf/images/random contains 5000 images
+ /tmp/tmp6nerfeb0/images/target contains 8144 images
+ /tmp/tmp6nerfeb0/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: 0.2268 - accuracy: 0.9224 - val_loss: 0.1540 - val_accuracy: 0.9498
+ 328/328 - 55s - loss: 0.2112 - accuracy: 0.9270 - val_loss: 0.1379 - val_accuracy: 0.9566
Epoch 2/3
- 328/328 - 52s - loss: 0.1022 - accuracy: 0.9605 - val_loss: 0.1117 - val_accuracy: 0.9675
+ 328/328 - 52s - loss: 0.0966 - accuracy: 0.9631 - val_loss: 0.1143 - val_accuracy: 0.9630
Epoch 3/3
- 328/328 - 52s - loss: 0.0698 - accuracy: 0.9733 - val_loss: 0.1227 - val_accuracy: 0.9653
+ 328/328 - 52s - loss: 0.0644 - accuracy: 0.9754 - val_loss: 0.1292 - val_accuracy: 0.9596
- <keras.callbacks.History object at 0x7f3b9a76f910>
+ <keras.callbacks.History object at 0x7f5e925ec1d0>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 44.392 seconds)
+ **Total running time of the script:** ( 5 minutes 7.304 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 f4d3a261e..fccfa74b7 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**05:37.131** total execution time for **how_to_work_with_microtvm** files:
+**06:01.022** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:44.392 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:07.304 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.724 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.474 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.730 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.889 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.284 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.353 | 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 50331175b..6551cb480 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
=================
-**00:40.374** total execution time for **how_to_work_with_relay** files:
+**00:41.993** 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``) | 00:30.059 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.600 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:07.857 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.872 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:02.451 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.513 | 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 |
+| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.008 | 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 42713a450..b3b6fdd77 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 0x7f3b1b6f3ef0>
+ <function my_cuda_math_rule at 0x7f5e22165d40>
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 380ec33ab..db453a421 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
=================
-**00:04.123** total execution time for **how_to_work_with_schedules** files:
+**00:04.227** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.873 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.954 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.029 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.014 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.525 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.545 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.513 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.530 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.102 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.014 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 2c6819571..da52dca7e 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/tmpqp_i2j13/input0.cc'\nsource_filename = \"/tmp/tmpqp_i2j13/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/tmpshpsgnys/input0.cc'\nsource_filename = \"/tmp/tmpshpsgnys/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 755bc6453..3180e0dc7 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
=================
-**00:20.869** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.359** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.862 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.352 | 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 a656717ed..52738b671 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.33s!
+ resnet18_v1 inference graph built in 23.24s!
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 907f50a92..9c4e37ab5 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.71s!
+ yolov3-tiny inference graph built in 16.13s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index 2de7a1ed4..e7f71eb10 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
=================
-**01:29.426** total execution time for **topic_vta_tutorials_frontend** files:
+**01:32.954** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.352 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.258 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.074 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.696 | 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 212a97aaa..bb6374e16 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
=================
-**00:03.264** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.309** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.863 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.890 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.401 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.420 | 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 c26343415..9a929ee3b 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
=================
-**00:00.708** total execution time for **topic_vta_tutorials** files:
+**00:00.760** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.378 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.405 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.330 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.355 | 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 4aa0172a4..95f260f38 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -205,13 +205,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- .T
-
-
@@ -335,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.343 ms
+ Execution time of this operator: 93.390 ms
@@ -451,11 +444,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 16.499 seconds)
-
-
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
.. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index d4ba6da5e..f06d08dbb 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.62/10.62 result: MeasureResult(costs=(0.025275727399999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.53354811668396, timestamp=1659739349.9832058) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.94/10.62 result: MeasureResult(costs=(0.0912391276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6082024574279785, timestamp=1659739352.1219757) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.89/11.89 result: MeasureResult(costs=(0.022570211200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5547225475311279, timestamp=1659739353.1586542) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.89 result: MeasureResult(costs=(0.1449266974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4410297870635986, timestamp=1659739356.1557446) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.69/11.89 result: MeasureResult(costs=(0.0727346324,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2974379062652588, timestamp=1659739357.5795963) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.79/11.89 result: MeasureResult(costs=(0.149680097,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5154078006744385, timestamp=1659739360.1345732) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.85/11.89 result: MeasureResult(costs=(0.3144699758,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.148500919342041, timestamp=1659739365.3292537) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.70/11.89 result: MeasureResult(costs=(0.025098832199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.582038402557373, timestamp=1659739365.9322722) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.64/11.89 result: MeasureResult(costs=(0.1640123738,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7210333347320557, timestamp=1659739368.7709506) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.67/11.89 result: MeasureResult(costs=(0.10047506580000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7173948287963867, timestamp=1659739370.5460224) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.05/10.05 result: MeasureResult(costs=(0.026717386599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5640602111816406, timestamp=1659967076.6930473) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.48/10.05 result: MeasureResult(costs=(0.10827101720000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.883862018585205, timestamp=1659967078.5899565) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.86/11.86 result: MeasureResult(costs=(0.0226247516,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5538632869720459, timestamp=1659967079.6540565) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.50/11.86 result: MeasureResult(costs=(0.178400016,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9779956340789795, timestamp=1659967083.2104225) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.69/11.86 result: MeasureResult(costs=(0.07283091859999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3083000183105469, timestamp=1659967085.1874716) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.76/11.86 result: MeasureResult(costs=(0.152874479,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6069319248199463, timestamp=1659967087.837515) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.86/11.86 result: MeasureResult(costs=(0.3123082974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.118847608566284, timestamp=1659967092.9983103) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.66/11.86 result: MeasureResult(costs=(0.025182184000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5502698421478271, timestamp=1659967093.564595) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.90/11.86 result: MeasureResult(costs=(0.1414735514,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3619203567504883, timestamp=1659967096.0469153) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.65/11.86 result: MeasureResult(costs=(0.10120940599999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7281930446624756, timestamp=1659967097.8335054) [('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 e581247ce..1d74adeeb 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 492.02085444000204, 'median': 492.04294385001504, 'std': 0.35129703142693447}
+ {'mean': 492.61969794000834, 'median': 492.56748635002623, 'std': 0.5595512100441674}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.30/ 17.30 GFLOPS | Progress: (4/20) | 6.28 s
[Task 1/25] Current/Best: 6.16/ 17.30 GFLOPS | Progress: (8/20) | 9.26 s
[Task 1/25] Current/Best: 11.57/ 22.81 GFLOPS | Progress: (12/20) | 11.73 s
[Task 1/25] Current/Best: 16.86/ 22.86 GFLOPS | Progress: (16/20) | 13.40 s
[Task 1/25] Current/Best: 11.63/ 23.88 GFLOPS | Progress: (20/20) | 15.14 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/ 12.78 GFLOPS | Progress: (4/20) | 3.90 s
[Task 2/25] Current/Best: 14.04/ 17.63 GFLOPS | Progress: (8/20) | 5.18 s
[Task 2/25] Current/Best: 21.08/ 21.08 GFLOPS | Progress: (12/20) | 6.51 s
[Task 2/25] Current/Best: 12.74/ 21.08 GFLOPS | Progress: (16/20) | 7.81 s
[Task 2/25] Current/Best: 20.19/ 21.08 GFLOPS | Progress: (20/20) | 9.40 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/ 10.60 GFLOPS | Progress: (4/20) | 5.86 s
[Task 3/25] Current/Best: 15.60/ 16.91 GFLOPS | Progress: (8/20) | 7.79 s
[Task 3/25] Current/Best: 14.92/ 16.91 GFLOPS | Progress: (12/20) | 9.50 s
[Task 3/25] Current/Best: 7.15/ 23.55 GFLOPS | Progress: (16/20) | 11.42 s
[Task 3/25] Current/Best: 12.60/ 23.55 GFLOPS | Progress: (20/20) | 16.02 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.56/ 20.47 GFLOPS | Progress: (4/20) | 2.37 s
[Task 4/25] Current/Best: 6.84/ 20.47 GFLOPS | Progress: (8/20) | 7.08 s
[Task 4/25] Current/Best: 22.59/ 22.59 GFLOPS | Progress: (12/20) | 12.11 s
[Task 4/25] Current/Best: 15.43/ 22.59 GFLOPS | Progress: (16/20) | 14.54 s
[Task 4/25] Current/Best: 13.57/ 22.59 GFLOPS | Progress: (20/20) | 16.59 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.73/ 10.48 GFLOPS | Progress: (4/20) | 2.59 s
[Task 5/25] Current/Best: 11.69/ 12.88 GFLOPS | Progress: (8/20) | 4.67 s
[Task 5/25] Current/Best: 11.82/ 18.13 GFLOPS | Progress: (12/20) | 7.86 s
[Task 5/25] Current/Best: 11.66/ 22.64 GFLOPS | Progress: (16/20) | 9.25 s
[Task 5/25] Current/Best: 12.00/ 22.64 GFLOPS | Progress: (20/20) | 11.12 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.20/ 20.70 GFLOPS | Progress: (4/20) | 4.12 s
[Task 6/25] Current/Best: 19.01/ 20.70 GFLOPS | Progress: (8/20) | 5.87 s
[Task 6/25] Current/Best: 13.35/ 20.70 GFLOPS | Progress: (12/20) | 7.80 s
[Task 6/25] Current/Best: 19.83/ 20.70 GFLOPS | Progress: (16/20) | 10.04 s
[Task 6/25] Current/Best: 3.72/ 20.70 GFLOPS | Progress: (20/20) | 12.55 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.23/ 13.01 GFLOPS | Progress: (4/20) | 3.51 s
[Task 7/25] Current/Best: 20.38/ 21.18 GFLOPS | Progress: (8/20) | 5.02 s
[Task 7/25] Current/Best: 16.06/ 21.18 GFLOPS | Progress: (12/20) | 6.91 s
[Task 7/25] Current/Best: 12.27/ 21.18 GFLOPS | Progress: (16/20) | 8.94 s
[Task 7/25] Current/Best: 6.31/ 21.69 GFLOPS | Progress: (20/20) | 11.37 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.95/ 13.82 GFLOPS | Progress: (4/20) | 2.93 s
[Task 8/25] Current/Best: 9.42/ 13.82 GFLOPS | Progress: (8/20) | 8.09 s
[Task 8/25] Current/Best: 12.60/ 13.82 GFLOPS | Progress: (12/20) | 14.54 s
[Task 8/25] Current/Best: 18.82/ 18.82 GFLOPS | Progress: (16/20) | 16.65 s
[Task 8/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (20/20) | 23.75 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.37/ 15.87 GFLOPS | Progress: (4/20) | 11.93 s
[Task 9/25] Current/Best: 23.41/ 23.41 GFLOPS | Progress: (8/20) | 13.73 s
[Task 9/25] Current/Best: 8.28/ 23.41 GFLOPS | Progress: (12/20) | 16.24 s
[Task 9/25] Current/Best: 17.99/ 23.41 GFLOPS | Progress: (16/20) | 19.10 s
[Task 9/25] Current/Best: 9.21/ 23.41 GFLOPS | Progress: (20/20) | 27.79 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (4/20) | 2.55 s
[Task 10/25] Current/Best: 15.63/ 18.12 GFLOPS | Progress: (8/20) | 4.17 s
[Task 10/25] Current/Best: 12.27/ 18.78 GFLOPS | Progress: (12/20) | 5.72 s
[Task 10/25] Current/Best: 19.24/ 20.27 GFLOPS | Progress: (16/20) | 6.82 s
[Task 10/25] Current/Best: 8.98/ 20.27 GFLOPS | Progress: (20/20
) | 8.33 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.27/ 18.13 GFLOPS | Progress: (4/20) | 3.30 s
[Task 11/25] Current/Best: 17.02/ 18.13 GFLOPS | Progress: (8/20) | 6.13 s
[Task 11/25] Current/Best: 16.76/ 18.13 GFLOPS | Progress: (12/20) | 8.18 s
[Task 11/25] Current/Best: 13.36/ 21.14 GFLOPS | Progress: (16/20) | 11.11 s
[Task 11/25] Current/Best: 19.45/ 21.57 GFLOPS | Progress: (20/20) | 13.22 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 17.45 GFLOPS | Progress: (4/20) | 5.77 s
[Task 12/25] Current/Best: 5.27/ 17.45 GFLOPS | Progress: (8/20) | 9.72 s
[Task 12/25] Current/Best: 18.87/ 18.95 GFLOPS | Progress: (12/20) | 11.70 s
[Task 12/25] Current/Best: 15.49/ 18.95 GFLOPS | Progress: (16/20) | 14.65 s
[Task 12/25] Current/Best: 15.18/ 18.95 GFLOPS | Progress: (20/20) | 16.60 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.86/ 17.28 GFLOPS | Progress: (4/20) | 3.75 s
[Task 13/25] Current/Best: 16.12/ 20.99 GFLOPS | Progress: (8/20) | 6.37 s
[Task 13/25] Current/Best: 19.60/ 21.17 GFLOPS | Progress: (12/20) | 9.35 s
[Task 13/25] Current/Best: 12.28/ 21.17 GFLOPS | Progress: (16/20) | 12.79 s
[Task 13/25] Current/Best: 18.84/ 21.17 GFLOPS | Progress: (20/20) | 15.12 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.02/ 13.28 GFLOPS | Progress: (4/20) | 3.40 s
[Task 14/25] Current/Best: 6.08/ 13.37 GFLOPS | Progress: (8/20) | 5.59 s
[Task 14/25] Current/Best: 21.00/ 21.00 GFLOPS | Progress: (12/20) | 8.26 s
[Task 14/25] Current/Best: 16.80/ 21.00 GFLOPS | Progress: (16/20) | 9.90 s Done.
-
[Task 14/25] Current/Best: 17.09/ 21.00 GFLOPS | Progress: (20/20) | 11.68 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.17/ 17.65 GFLOPS | Progress: (4/20) | 2.71 s
[Task 15/25] Current/Best: 14.30/ 17.80 GFLOPS | Progress: (8/20) | 4.07 s
[Task 15/25] Current/Best: 10.41/ 22.38 GFLOPS | Progress: (12/20) | 6.34 s
[Task 15/25] Current/Best: 20.45/ 22.38 GFLOPS | Progress: (16/20) | 10.08 s
[Task 15/25] Current/Best: 9.72/ 22.38 GFLOPS | Progress: (20/20) | 11.08 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.90/ 20.90 GFLOPS | Progress: (4/20) | 2.91 s
[Task 16/25] Current/Best: 3.04/ 20.90 GFLOPS | Progress: (8/20) | 4.53 s
[Task 16/25] Current/Best: 19.61/ 20.90 GFLOPS | Progress: (12/20) | 5.76 s
[Task 16/25] Current/Best: 18.28/ 20.90 GFLOPS | Progress: (16/20)
| 7.12 s
[Task 16/25] Current/Best: 10.02/ 22.39 GFLOPS | Progress: (20/20) | 9.29 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.73/ 19.01 GFLOPS | Progress: (4/20) | 4.78 s
[Task 17/25] Current/Best: 14.42/ 23.42 GFLOPS | Progress: (8/20) | 7.67 s
[Task 17/25] Current/Best: 17.41/ 23.42 GFLOPS | Progress: (12/20) | 9.71 s
[Task 17/25] Current/Best: 16.56/ 23.42 GFLOPS | Progress: (16/20) | 11.93 s
[Task 17/25] Current/Best: 10.06/ 23.42 GFLOPS | Progress: (20/20) | 14.09 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.33/ 17.21 GFLOPS | Progress: (4/20) | 3.80 s
[Task 18/25] Current/Best: 10.57/ 19.63 GFLOPS | Progress: (8/20) | 7.46 s
[Task 18/25] Current/Best: 19.63/ 19.63 GFLOPS | Progress: (12/20) | 9.40 s
[Task 18/25] Current/Best: 9.99/ 19.63 GFLOPS | Progress: (16/20) | 13.34 s
[Task 18/25] Current/Best: 20.71/ 20.71 GFLOPS | Progress: (20/20) | 14.83 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.16/ 20.44 GFLOPS | Progress: (4/20) | 6.13 s
[Task 19/25] Current/Best: 2.60/ 20.44 GFLOPS | Progress: (8/20) | 9.48 s
[Task 19/25] Current/Best: 20.32/ 21.28 GFLOPS | Progress: (12/20) | 12.48 s
[Task 19/25] Current/Best: 14.16/ 21.46 GFLOPS | Progress: (16/20) | 15.54 s
[Task 19/25] Current/Best: 2.70/ 23.74 GFLOPS | Progress: (20/20) | 18.35 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.14/ 15.20 GFLOPS | Progress: (4/20) | 3.36 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.53/ 17.53 GFLOPS | Progress: (4/20) | 6.32 s
[Task 1/25] Current/Best: 6.15/ 17.53 GFLOPS | Progress: (8/20) | 9.35 s
[Task 1/25] Current/Best: 11.54/ 22.70 GFLOPS | Progress: (12/20) | 11.86 s
[Task 1/25] Current/Best: 16.83/ 22.70 GFLOPS | Progress: (16/20) | 13.55 s
[Task 1/25] Current/Best: 11.57/ 23.73 GFLOPS | Progress: (20/20) | 15.29 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.29/ 12.93 GFLOPS | Progress: (4/20) | 3.92 s
[Task 2/25] Current/Best: 13.94/ 17.84 GFLOPS | Progress: (8/20) | 5.25 s
[Task 2/25] Current/Best: 20.88/ 20.88 GFLOPS | Progress: (12/20) | 6.60 s
[Task 2/25] Current/Best: 12.01/ 20.88 GFLOPS | Progress: (16/20) | 7.86 s
[Task 2/25] Current/Best: 19.31/ 20.88 GFLOPS | Progress: (20/20) | 9.48 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/ 10.56 GFLOPS | Progress: (4/20) | 5.89 s
[Task 3/25] Current/Best: 15.60/ 16.89 GFLOPS | Progress: (8/20) | 7.81 s
[Task 3/25] Current/Best: 14.93/ 16.89 GFLOPS | Progress: (12/20) | 9.55 s
[Task 3/25] Current/Best: 7.24/ 23.78 GFLOPS | Progress: (16/20) | 11.45 s
[Task 3/25] Current/Best: 12.55/ 23.78 GFLOPS | Progress: (20/20) | 16.01 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.53/ 20.50 GFLOPS | Progress: (4/20) | 2.41 s
[Task 4/25] Current/Best: 6.66/ 20.50 GFLOPS | Progress: (8/20) | 7.14 s
[Task 4/25] Current/Best: 22.21/ 22.21 GFLOPS | Progress: (12/20) | 12.07 s
[Task 4/25] Current/Best: 16.79/ 22.21 GFLOPS | Progress: (16/20) | 14.46 s
[Task 4/25] Current/Best: 13.21/ 22.21 GFLOPS | Progress: (20/20) | 16.56 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.39/ 10.35 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.79/ 12.79 GFLOPS | Progress: (8/20) | 4.68 s
[Task 5/25] Current/Best: 11.09/ 18.08 GFLOPS | Progress: (12/20) | 7.90 s
[Task 5/25] Current/Best: 11.87/ 22.72 GFLOPS | Progress: (16/20) | 9.33 s
[Task 5/25] Current/Best: 11.90/ 22.72 GFLOPS | Progress: (20/20) | 11.30 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.20/ 20.66 GFLOPS | Progress: (4/20) | 4.14 s
[Task 6/25] Current/Best: 18.90/ 20.66 GFLOPS | Progress: (8/20) | 5.89 s
[Task 6/25] Current/Best: 13.26/ 20.66 GFLOPS | Progress: (12/20) | 7.85 s
[Task 6/25] Current/Best: 20.03/ 20.66 GFLOPS | Progress: (16/20) | 10.13 s
[Task 6/25] Current/Best: 3.73/ 20.66 GFLOPS | Progress: (20/20) | 12.65 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.18/ 12.97 GFLOPS | Progress: (4/20) | 3.66 s
[Task 7/25] Current/Best: 20.22/ 21.09 GFLOPS | Progress: (8/20) | 5.19 s
[Task 7/25] Current/Best: 16.12/ 21.09 GFLOPS | Progress: (12/20) | 7.12 s
[Task 7/25] Current/Best: 12.23/ 21.09 GFLOPS | Progress: (16/20) | 9.17 s
[Task 7/25] Current/Best: 6.46/ 21.71 GFLOPS | Progress: (20/20) | 11.62 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.99/ 14.17 GFLOPS | Progress: (4/20) | 2.95 s
[Task 8/25] Current/Best: 9.71/ 14.17 GFLOPS | Progress: (8/20) | 8.06 s
[Task 8/25] Current/Best: 12.82/ 14.17 GFLOPS | Progress: (12/20) | 14.56 s
[Task 8/25] Current/Best: 18.77/ 18.77 GFLOPS | Progress: (16/20) | 16.67 s
[Task 8/25] Current/Best: 19.93/ 19.93 GFLOPS | Progress: (20/20) | 23.75 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.35/ 15.58 GFLOPS | Progress: (4/20) | 11.99 s
[Task 9/25] Current/Best: 23.53/ 23.53 GFLOPS | Progress: (8/20) | 13.80 s
[Task 9/25] Current/Best: 8.26/ 23.53 GFLOPS | Progress: (12/20) | 16.33 s
[Task 9/25] Current/Best: 18.00/ 23.53 GFLOPS | Progress: (16/20) | 19.18 s
[Task 9/25] Current/Best: 9.26/ 23.53 GFLOPS | Progress: (20/20) | 27.74 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (4/20) | 2.58 s
[Task 10/25] Current/Best: 15.57/ 18.23 GFLOPS | Progress: (8/20) | 4.20 s
[Task 10/25] Current/Best: 11.51/ 18.92 GFLOPS | Progress: (12/20) | 5.76 s
[Task 10/25] Current/Best: 19.15/ 20.43 GFLOPS | Progress: (16/20) | 6.86 s
[Task 10/25] Current/Best: 8.88/ 20.43 GFLOPS | Progress: (20/20
) | 8.40 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.37/ 18.16 GFLOPS | Progress: (4/20) | 3.39 s
[Task 11/25] Current/Best: 16.90/ 18.16 GFLOPS | Progress: (8/20) | 6.21 s
[Task 11/25] Current/Best: 17.93/ 18.16 GFLOPS | Progress: (12/20) | 8.26 s
[Task 11/25] Current/Best: 13.20/ 21.19 GFLOPS | Progress: (16/20) | 11.22 s
[Task 11/25] Current/Best: 19.44/ 21.60 GFLOPS | Progress: (20/20) | 13.31 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.82/ 18.05 GFLOPS | Progress: (4/20) | 5.76 s
[Task 12/25] Current/Best: 5.28/ 18.05 GFLOPS | Progress: (8/20) | 9.66 s
[Task 12/25] Current/Best: 18.86/ 18.89 GFLOPS | Progress: (12/20) | 11.65 s
[Task 12/25] Current/Best: 15.47/ 18.89 GFLOPS | Progress: (16/20) | 14.59 s
[Task 12/25] Current/Best: 15.14/ 18.97 GFLOPS | Progress: (20/20) | 16.51 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.70/ 17.30 GFLOPS | Progress: (4/20) | 3.79 s
[Task 13/25] Current/Best: 16.00/ 21.08 GFLOPS | Progress: (8/20) | 6.38 s
[Task 13/25] Current/Best: 19.62/ 21.72 GFLOPS | Progress: (12/20) | 9.46 s
[Task 13/25] Current/Best: 12.25/ 21.72 GFLOPS | Progress: (16/20) | 12.94 s
[Task 13/25] Current/Best: 18.82/ 21.72 GFLOPS | Progress: (20/20) | 15.29 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.88/ 13.19 GFLOPS | Progress: (4/20) | 3.44 s
[Task 14/25] Current/Best: 6.08/ 13.34 GFLOPS | Progress: (8/20) | 5.66 s
[Task 14/25] Current/Best: 19.81/ 19.81 GFLOPS | Progress: (12/20) | 8.35 s
[Task 14/25] Current/Best: 17.20/ 19.81 GFLOPS | Progress: (16/20) | 10.00 s Done.
+
[Task 14/25] Current/Best: 16.98/ 19.81 GFLOPS | Progress: (20/20) | 11.81 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.16/ 17.66 GFLOPS | Progress: (4/20) | 2.73 s
[Task 15/25] Current/Best: 14.41/ 18.05 GFLOPS | Progress: (8/20) | 4.08 s
[Task 15/25] Current/Best: 10.39/ 22.36 GFLOPS | Progress: (12/20) | 6.30 s
[Task 15/25] Current/Best: 20.43/ 22.36 GFLOPS | Progress: (16/20) | 9.92 s
[Task 15/25] Current/Best: 9.71/ 22.36 GFLOPS | Progress: (20/20) | 10.94 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.60/ 20.60 GFLOPS | Progress: (4/20) | 2.96 s
[Task 16/25] Current/Best: 3.00/ 20.60 GFLOPS | Progress: (8/20) | 4.58 s
[Task 16/25] Current/Best: 19.06/ 20.60 GFLOPS | Progress: (12/20) | 5.81 s
[Task 16/25] Current/Best: 17.57/ 20.60 GFLOPS | Progress: (16/20) |
7.19 s
[Task 16/25] Current/Best: 10.02/ 22.01 GFLOPS | Progress: (20/20) | 9.34 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.47/ 18.76 GFLOPS | Progress: (4/20) | 4.81 s
[Task 17/25] Current/Best: 14.36/ 23.29 GFLOPS | Progress: (8/20) | 7.61 s
[Task 17/25] Current/Best: 17.01/ 23.29 GFLOPS | Progress: (12/20) | 9.67 s
[Task 17/25] Current/Best: 17.26/ 23.29 GFLOPS | Progress: (16/20) | 11.88 s
[Task 17/25] Current/Best: 10.01/ 23.29 GFLOPS | Progress: (20/20) | 14.03 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.33/ 18.00 GFLOPS | Progress: (4/20) | 3.81 s
[Task 18/25] Current/Best: 10.53/ 19.63 GFLOPS | Progress: (8/20) | 7.47 s
[Task 18/25] Current/Best: 18.89/ 19.63 GFLOPS | Progress: (12/20) | 9.43 s
[Task 18/25] Current/Best: 10.13/ 19.63 GFLOPS | Progress: (16/20) | 13.29 s
[Task 18/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (20/20) | 14.80 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.23/ 20.25 GFLOPS | Progress: (4/20) | 6.16 s
[Task 19/25] Current/Best: 2.60/ 20.25 GFLOPS | Progress: (8/20) | 9.52 s
[Task 19/25] Current/Best: 19.15/ 21.73 GFLOPS | Progress: (12/20) | 12.47 s
[Task 19/25] Current/Best: 13.89/ 21.73 GFLOPS | Progress: (16/20) | 15.44 s
[Task 19/25] Current/Best: 2.70/ 23.73 GFLOPS | Progress: (20/20) | 18.25 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.55/ 15.16 GFLOPS | Progress: (4/20) | 3.38 s Done.
Done.
-
[Task 20/25] Current/Best: 9.73/ 15.20 GFLOPS | Progress: (8/20) | 6.79 s
[Task 20/25] Current/Best: 2.29/ 16.59 GFLOPS | Progress: (12/20) | 10.72 s
[Task 20/25] Current/Best: 12.52/ 16.59 GFLOPS | Progress: (16/20) | 14.47 s
[Task 20/25] Current/Best: 13.64/ 22.22 GFLOPS | Progress: (20/20) | 16.54 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.69 GFLOPS | Progress: (4/20) | 3.29 s
[Task 21/25] Current/Best: 14.66/ 17.69 GFLOPS | Progress: (8/20) | 4.88 s
[Task 21/25] Current/Best: 1.61/ 17.69 GFLOPS | Progress: (12/20) | 7.00 s
[Task 21/25] Current/Best: 17.66/ 17.69 GFLOPS | Progress: (16/20) | 10.51 s
[Task 21/25] Current/Best: 4.46/ 17.69 GFLOPS | Progress: (20/20) | 17.74 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.71/ 17.00 GFLOPS | Progress: (4/20
) | 2.65 s
[Task 22/25] Current/Best: 8.67/ 21.86 GFLOPS | Progress: (8/20) | 4.69 s
[Task 22/25] Current/Best: 19.99/ 21.86 GFLOPS | Progress: (12/20) | 7.06 s
[Task 22/25] Current/Best: 15.43/ 21.86 GFLOPS | Progress: (16/20) | 9.17 s
[Task 22/25] Current/Best: 14.16/ 21.86 GFLOPS | Progress: (20/20) | 10.90 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.69/ 20.64 GFLOPS | Progress: (4/20) | 3.23 s
[Task 23/25] Current/Best: 14.43/ 20.64 GFLOPS | Progress: (8/20) | 6.61 s
[Task 23/25] Current/Best: 20.99/ 21.87 GFLOPS | Progress: (12/20) | 8.45 s
[Task 23/25] Current/Best: 6.47/ 21.87 GFLOPS | Progress: (16/20) | 15.49 s
[Task 23/25] Current/Best: 7.92/ 21.87 GFLOPS | Progress: (20/20) | 19.67 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.49/ 8.49 GFLOPS | Progress: (4/20) | 11.79 s
[Task 24/25] Current/Best: 2.18/ 8.49 GFLOPS | Progress: (8/20) | 22.79 s
[Task 24/25] Current/Best: 4.58/ 8.49 GFLOPS | Progress: (12/20) | 34.30 s Done.
-
[Task 24/25] Current/Best: 5.99/ 8.75 GFLOPS | Progress: (16/20) | 39.92 s
[Task 24/25] Current/Best: 3.38/ 8.98 GFLOPS | Progress: (20/20) | 45.82 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/ 2.75 GFLOPS | Progress: (4/20) | 11.58 s
[Task 25/25] Current/Best: 5.80/ 7.75 GFLOPS | Progress: (8/20) | 22.89 s
[Task 25/25] Current/Best: 5.84/ 7.75 GFLOPS | Progress: (12/20) | 34.32 s
[Task 25/25] Current/Best: 5.78/ 8.69 GFLOPS | Progress: (16/20) | 36.16 s
[Task 25/25] Current/Best: 2.86/ 9.28 GFLOPS | Progress: (20/20) | 46.86 s
+
[Task 20/25] Current/Best: 10.16/ 15.16 GFLOPS | Progress: (8/20) | 6.76 s
[Task 20/25] Current/Best: 2.32/ 16.73 GFLOPS | Progress: (12/20) | 10.70 s
[Task 20/25] Current/Best: 12.50/ 16.73 GFLOPS | Progress: (16/20) | 14.48 s
[Task 20/25] Current/Best: 12.67/ 22.05 GFLOPS | Progress: (20/20) | 16.60 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.72 GFLOPS | Progress: (4/20) | 3.32 s
[Task 21/25] Current/Best: 14.65/ 17.72 GFLOPS | Progress: (8/20) | 4.91 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 7.06 s
[Task 21/25] Current/Best: 18.11/ 18.11 GFLOPS | Progress: (16/20) | 10.58 s
[Task 21/25] Current/Best: 4.46/ 18.11 GFLOPS | Progress: (20/20) | 17.89 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
) | 2.71 s
[Task 22/25] Current/Best: 8.76/ 22.01 GFLOPS | Progress: (8/20) | 4.67 s
[Task 22/25] Current/Best: 19.89/ 22.01 GFLOPS | Progress: (12/20) | 7.07 s
[Task 22/25] Current/Best: 15.42/ 22.01 GFLOPS | Progress: (16/20) | 9.20 s
[Task 22/25] Current/Best: 14.30/ 22.01 GFLOPS | Progress: (20/20) | 10.94 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.52/ 20.38 GFLOPS | Progress: (4/20) | 3.29 s
[Task 23/25] Current/Best: 15.20/ 20.38 GFLOPS | Progress: (8/20) | 6.67 s
[Task 23/25] Current/Best: 21.04/ 21.67 GFLOPS | Progress: (12/20) | 8.54 s
[Task 23/25] Current/Best: 6.42/ 21.67 GFLOPS | Progress: (16/20) | 15.74 s
[Task 23/25] Current/Best: 7.82/ 21.67 GFLOPS | Progress: (20/20) | 19.97 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.42/ 8.42 GFLOPS | Progress: (4/20) | 11.82 s
[Task 24/25] Current/Best: 2.14/ 8.42 GFLOPS | Progress: (8/20) | 22.90 s
[Task 24/25] Current/Best: 4.21/ 8.42 GFLOPS | Progress: (12/20) | 34.45 s Done.
+
[Task 24/25] Current/Best: 6.51/ 8.59 GFLOPS | Progress: (16/20) | 40.11 s
[Task 24/25] Current/Best: 3.33/ 8.93 GFLOPS | Progress: (20/20) | 46.08 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.56/ 2.76 GFLOPS | Progress: (4/20) | 11.62 s
[Task 25/25] Current/Best: 5.96/ 8.05 GFLOPS | Progress: (8/20) | 22.93 s
[Task 25/25] Current/Best: 5.93/ 8.05 GFLOPS | Progress: (12/20) | 34.43 s
[Task 25/25] Current/Best: 5.79/ 8.83 GFLOPS | Progress: (16/20) | 36.19 s
[Task 25/25] Current/Best: 2.87/ 8.92 GFLOPS | Progress: (20/20) | 46.86 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 405.58891014001347, 'median': 405.3527530000338, 'std': 1.537552474111033}
- unoptimized: {'mean': 492.02085444000204, 'median': 492.04294385001504, 'std': 0.35129703142693447}
+ optimized: {'mean': 412.0232883299832, 'median': 411.7353187500157, 'std': 1.4984257026444192}
+ unoptimized: {'mean': 492.61969794000834, 'median': 492.56748635002623, 'std': 0.5595512100441674}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 21.509 seconds)
+ **Total running time of the script:** ( 10 minutes 26.917 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 891c52071..8360d0b4b 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
- 1.319e-07 secs/op
+ 1.399e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index f0164369d..5f4856575 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, 0x11cbcd50)), stage(b, placeholder(b, 0x1feb5990)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x19038a50)), stage(b, placeholder(b, 0x2928b40)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 8045e233c..483f8b050 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
=================
-**13:32.919** total execution time for **tutorial** files:
+**13:11.505** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:21.509 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:26.917 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:16.499 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.525 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.657 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:48.459 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:29.936 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.300 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.985 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.671 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.691 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.757 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.501 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.705 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.135 | 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_introduction.py` (``introduction.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 1930183e8..da770c159 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: 0.000006
+ Numpy running time: 0.000007
+ naive: 0.000007
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.842779996281025e-06 1.0
- naive 5.8289e-06 0.7432186039598219
- parallel 6.063e-06 0.7730677136009195
- vector 2.45588e-05 3.1313896362827416
+ numpy 7.0651600071869326e-06 1.0
+ naive 6.5632e-06 0.9289527757791302
+ parallel 6.2036e-06 0.8780551316161951
+ vector 2.47307e-05 3.5003736610130627
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019211
+ Numpy running time: 0.018248
@@ -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: 3.311686
+ none: 3.301640
@@ -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: 0.305939
+ blocking: 0.303194
@@ -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: 0.339582
+ vectorization: 0.338449
@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: 0.111890
+ loop permutation: 0.117722
@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: 0.108433
+ array packing: 0.110805
@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: 0.111190
+ block caching: 0.111982
@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: 0.144564
+ parallelization: 0.146591
@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 3.3116862459000003 1.0
- blocking 0.3059394401 0.0923817709116512
- vectorization 0.3395817054 0.10254042206456475
- loop permutation 0.11189047869999999 0.033786557781107694
- array packing 0.1084330341 0.03274254444672844
- block caching 0.1111899645 0.0335750298319044
- parallelization 0.1445639918 0.04365268357743008
+ none 3.3016403708999995 1.0
+ blocking 0.30319396029999995 0.0918313099670973
+ vectorization 0.3384489645 0.10250933671729415
+ loop permutation 0.117721645 0.03565550204606629
+ array packing 0.1108045183 0.03356044446167092
+ block caching 0.1119818961 0.03391704835177875
+ parallelization 0.1465905639 0.04439931289671038
diff --git a/docs/commit_hash b/docs/commit_hash
index a6e2f0bfe..c1f80d584 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-5821c1240e18a137dfb0afe8810e97e50fd869ca
+b4e36c61fcf07e3e75649e72bd97a35603edc2b6
diff --git a/docs/genindex.html b/docs/genindex.html
index c7aca47f6..b26a45a05 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -3259,6 +3259,8 @@
<li><a href="reference/api/python/tir.html#tvm.tir.transform.RemoveAssume">RemoveAssume() (in module tvm.tir.transform)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.RemoveNoOp">RemoveNoOp() (in module tvm.tir.transform)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.transform.RemoveStoreUndef">RemoveStoreUndef() (in module tvm.tir.transform)</a>
</li>
<li><a href="reference/api/python/relay/transform.html#tvm.relay.transform.RemoveUnusedFunctions">RemoveUnusedFunctions() (in module tvm.relay.transform)</a>
</li>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index d255a8217..3f055aefb 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.894 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.333 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 f2d718c7b..4954e0e0a 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipbe3d274f-1a78-4877-be83-f3137dc20d92 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.zip3b21b8e4-f5d5-4fc9-bbad-d7f754b399dd 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 10820ca43..3080d7b69 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,13 +432,13 @@ 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, 60.6MB/s]
- 29%|##9 | 12.1M/41.5M [00:00<00:00, 52.8MB/s]
- 41%|####1 | 17.2M/41.5M [00:00<00:00, 45.1MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 47.6MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 47.4MB/s]
- 94%|#########3| 39.0M/41.5M [00:00<00:00, 54.1MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 49.6MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 36.4MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 34.1MB/s]
+ 53%|#####2 | 21.9M/41.5M [00:00<00:00, 46.9MB/s]
+ 65%|######5 | 27.2M/41.5M [00:00<00:00, 33.6MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 33.1MB/s]
+ 86%|########5 | 35.6M/41.5M [00:01<00:00, 32.9MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 37.1MB/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 f0353feba..d0054bb73 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,11 +414,8 @@ 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]
- 11%|#1 | 4.93M/44.7M [00:00<00:00, 51.7MB/s]
- 22%|##2 | 9.86M/44.7M [00:00<00:00, 49.4MB/s]
- 67%|######7 | 30.1M/44.7M [00:00<00:00, 122MB/s]
- 94%|#########3| 41.9M/44.7M [00:00<00:00, 102MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 95.6MB/s]
+ 50%|##### | 22.4M/44.7M [00:00<00:00, 235MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 255MB/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 3ca26c3e1..1879a74f3 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.570 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.013 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 c7eff1a84..ff0961174 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>04:54.167</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:11.018</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:00.894</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:06.013</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>01:00.570</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:03.333</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:38.925</p></td>
+<td><p>00:39.701</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:27.202</p></td>
+<td><p>00:28.167</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>00:24.396</p></td>
+<td><p>00:26.821</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>00:24.311</p></td>
+<td><p>00:25.985</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>00:21.427</p></td>
+<td><p>00:23.366</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.554</p></td>
+<td><p>00:20.187</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>00:14.626</p></td>
+<td><p>00:15.024</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>00:02.262</p></td>
+<td><p>00:02.421</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 b7aadbf92..9421a3971 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.5677 15.5340 15.7678 15.4708 0.0899
+ 15.7922 15.7958 16.0043 15.6177 0.1204
</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 b149c6e41..4498da20f 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,15 +436,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|1 | 3.26M/170M [00:00<00:05, 33.4MB/s]
- 4%|3 | 6.45M/170M [00:00<00:05, 32.1MB/s]
- 19%|#8 | 31.9M/170M [00:00<00:01, 137MB/s]
- 34%|###3 | 57.4M/170M [00:00<00:00, 178MB/s]
- 49%|####9 | 84.0M/170M [00:00<00:00, 213MB/s]
- 64%|######4 | 110M/170M [00:00<00:00, 231MB/s]
- 79%|#######9 | 135M/170M [00:00<00:00, 242MB/s]
- 94%|#########4| 160M/170M [00:00<00:00, 250MB/s]
-100%|##########| 170M/170M [00:00<00:00, 207MB/s]
+ 10%|# | 17.5M/170M [00:00<00:00, 184MB/s]
+ 24%|##4 | 41.5M/170M [00:00<00:00, 224MB/s]
+ 39%|###8 | 65.6M/170M [00:00<00:00, 237MB/s]
+ 52%|#####2 | 88.9M/170M [00:00<00:00, 240MB/s]
+ 66%|######6 | 113M/170M [00:00<00:00, 244MB/s]
+ 80%|######## | 136M/170M [00:00<00:00, 242MB/s]
+ 94%|#########3| 160M/170M [00:00<00:00, 244MB/s]
+100%|##########| 170M/170M [00:00<00:00, 239MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -539,7 +538,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 53.356 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 57.376 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 9a9d49de0..3dae40066 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,8 +480,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 85%|########5 | 11.6M/13.6M [00:00<00:00, 116MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 124MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 173MB/s]
</pre></div>
</div>
</div>
@@ -570,7 +569,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.1342 90.0681 92.7173 89.8600 0.3264
+ 90.3919 90.1951 102.9096 90.0938 1.3306
</pre></div>
</div>
<div class="admonition note">
@@ -609,7 +608,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.811 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.733 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 e8279545f..ae4bf5f46 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.2781 118.3908 120.2176 116.5204 0.7695
+ 120.3294 120.2923 121.7232 119.4218 0.3800
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 57.365 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 2.396 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 e91bc5f70..0bb23c4ce 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.287 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.418 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 c68e88f33..4db639cf3 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,23 +441,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|5 | 6654/132723 [00:00<00:01, 66531.81KB/s]
- 11%|#1 | 14815/132723 [00:00<00:01, 75398.60KB/s]
- 17%|#7 | 22834/132723 [00:00<00:01, 77584.37KB/s]
- 23%|##3 | 30891/132723 [00:00<00:01, 78756.00KB/s]
- 30%|##9 | 39190/132723 [00:00<00:01, 80058.14KB/s]
- 36%|###5 | 47273/132723 [00:00<00:01, 80316.85KB/s]
- 42%|####1 | 55454/132723 [00:00<00:00, 80801.86KB/s]
- 48%|####7 | 63595/132723 [00:00<00:00, 80993.47KB/s]
- 54%|#####4 | 71708/132723 [00:00<00:00, 81035.06KB/s]
- 60%|###### | 79874/132723 [00:01<00:00, 81225.18KB/s]
- 66%|######6 | 88018/132723 [00:01<00:00, 81288.02KB/s]
- 72%|#######2 | 96180/132723 [00:01<00:00, 81387.59KB/s]
- 79%|#######8 | 104319/132723 [00:01<00:00, 80967.09KB/s]
- 85%|########4 | 112431/132723 [00:01<00:00, 81010.63KB/s]
- 91%|#########1| 120841/132723 [00:01<00:00, 81935.72KB/s]
- 97%|#########7| 129131/132723 [00:01<00:00, 82224.03KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 79923.31KB/s]
+ 5%|4 | 6621/132723 [00:00<00:01, 66206.43KB/s]
+ 11%|#1 | 15039/132723 [00:00<00:01, 76773.97KB/s]
+ 18%|#7 | 23502/132723 [00:00<00:01, 80358.44KB/s]
+ 24%|##4 | 31938/132723 [00:00<00:01, 81935.86KB/s]
+ 30%|### | 40434/132723 [00:00<00:01, 83024.43KB/s]
+ 37%|###6 | 48895/132723 [00:00<00:01, 83561.29KB/s]
+ 43%|####3 | 57407/132723 [00:00<00:00, 84069.17KB/s]
+ 50%|####9 | 65948/132723 [00:00<00:00, 84494.56KB/s]
+ 56%|#####6 | 74447/132723 [00:00<00:00, 84647.31KB/s]
+ 62%|######2 | 82941/132723 [00:01<00:00, 84734.39KB/s]
+ 69%|######8 | 91438/132723 [00:01<00:00, 84803.30KB/s]
+ 75%|#######5 | 99933/132723 [00:01<00:00, 84842.53KB/s]
+ 82%|########1 | 108418/132723 [00:01<00:00, 84808.68KB/s]
+ 88%|########8 | 116899/132723 [00:01<00:00, 67411.23KB/s]
+ 94%|#########4| 125344/132723 [00:01<00:00, 71759.77KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 79166.68KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -500,7 +499,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.501 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 34.566 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 6e8b7b1f0..88e74a0f2 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:00.673</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:27.444</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:53.356</p></td>
+<td><p>02:57.376</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>02:32.501</p></td>
+<td><p>02:34.566</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:57.365</p></td>
+<td><p>02:02.396</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>01:16.287</p></td>
+<td><p>01:29.418</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>01:07.811</p></td>
+<td><p>01:08.733</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>00:28.645</p></td>
+<td><p>00:29.625</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.480</p></td>
+<td><p>00:22.870</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.222</p></td>
+<td><p>00:22.454</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index ea3168b43..8ef9be2f1 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf00b1f96-5da5-44c2-b4b4-2f21a2c4276c 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.zip0a9d853e-d3fb-4715-bcc5-659765878364 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 ea5b2f695..3605d3323 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.297</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.836</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:36.898</p></td>
+<td><p>00:37.682</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>00:02.440</p></td>
+<td><p>00:02.208</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>00:00.951</p></td>
+<td><p>00:00.937</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 637272b4e..4b91f495c 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 9820us [9820us] (44.78%; 44.78%)
-FoldScaleAxis: 12108us [12us] (55.22%; 55.22%)
- FoldConstant: 12097us [2046us] (55.16%; 99.90%)
- InferType: 10050us [10050us] (45.83%; 83.08%)
+InferType: 6544us [6544us] (45.34%; 45.34%)
+FoldScaleAxis: 7888us [7us] (54.66%; 54.66%)
+ FoldConstant: 7881us [1614us] (54.61%; 99.92%)
+ InferType: 6268us [6268us] (43.43%; 79.52%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 9513us [9513us] (44.85%; 44.85%)
-FoldScaleAxis: 11698us [10us] (55.15%; 55.15%)
- FoldConstant: 11688us [2288us] (55.10%; 99.91%)
- InferType: 9400us [9400us] (44.31%; 80.42%)
+InferType: 6298us [6298us] (44.82%; 44.82%)
+FoldScaleAxis: 7753us [5us] (55.18%; 55.18%)
+ FoldConstant: 7748us [1639us] (55.14%; 99.94%)
+ InferType: 6109us [6109us] (43.48%; 78.85%)
</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 16ddff474..4206838dd 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 50.286589 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 37.907445 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 e3f41d817..0d890fa8c 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.002721 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.297706 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 91f7bd20a..1c7c95354 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018111
-Baseline: 3.311390
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018634
+Baseline: 3.290959
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.295603
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296151
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.333779
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336130
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114166
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118537
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110476
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111252
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111631
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111293
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144850
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145257
</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 c0e3afd64..ff790483b 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.003</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.097</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.770</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>00:01.229</p></td>
+<td><p>00:01.239</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>00:01.004</p></td>
+<td><p>00:01.012</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 d27106f00..868ced9cf 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:57.842</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:15.999</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:12.949</p></td>
+<td><p>03:28.171</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:22.035</p></td>
+<td><p>01:24.008</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>00:46.184</p></td>
+<td><p>00:46.414</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>00:19.479</p></td>
+<td><p>00:19.644</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.642</p></td>
+<td><p>00:08.903</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>00:08.552</p></td>
+<td><p>00:08.859</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 927d4a34f..df21a98b8 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,483 +491,476 @@ 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" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [392]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [256]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
- 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[14] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[15] = 0f32
for (rc.outer.outer: int32, 0, 64) {
for (ry.outer.outer: int32, 0, 3) {
let cse_var_2: int32 = (rc.outer.outer*72)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
- }
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [392], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 90)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 188)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 286)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [256], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 8)*9)) + cse_var_1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 98), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 2), 8)*9)) + cse_var_1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 60), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 8)*9)) + cse_var_1)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 128)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 160)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 192)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 224)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 136)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 168)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 200)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 232)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 97)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 129)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 161)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 193)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 137)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 169)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 201)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 233)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 98)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 130)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 162)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 194)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 226)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 170)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 202)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 234)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 131)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 163)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 195)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 227)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 139)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 203)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 235)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 100)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 132)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 164)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 196)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 140)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 172)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 204)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 236)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 101)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 133)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 165)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 197)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 229)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 173)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 205)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 237)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 134)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 166)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 198)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 230)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 142)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 174)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 206)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 238)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 103)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 135)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 167)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 199)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 143)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 175)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 207)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 239)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 91)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 189)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 287)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 8)*9)) + cse_var_1) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 98), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 2), 8)*9)) + cse_var_1) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 60), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 8)*9)) + cse_var_1) + 1)]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 128)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 160)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 192)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 224)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 136)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 168)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 200)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 232)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 97)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 129)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 161)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 193)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 137)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 169)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 201)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 233)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 98)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 130)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 162)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 194)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 226)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 170)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 202)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 234)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 131)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 163)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 195)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 227)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 139)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 203)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 235)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 100)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 132)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 164)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 196)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 140)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 172)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 204)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 236)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 101)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 133)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 165)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 197)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 229)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 173)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 205)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 237)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 134)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 166)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 198)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 230)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 142)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 174)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 206)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 238)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 103)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 135)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 167)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 199)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 143)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 175)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 207)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 239)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 92)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 190)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((rc.outer.outer*392) + (ry.outer.outer*7)) + threadIdx.x_1) + 288)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 8)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 8)*9)) + cse_var_1) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 98), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 2), 8)*9)) + cse_var_1) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 60), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 8)*4608)) + cse_var_2) + (floormod((threadIdx.x_2 + 4), 8)*9)) + cse_var_1) + 2)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 128)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 160)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 192)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 224)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 136)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 168)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 200)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 232)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 97)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 129)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 161)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 193)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 137)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 169)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 201)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 233)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 98)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 130)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 162)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 194)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 226)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 170)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 202)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 234)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 131)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 163)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 195)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 227)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 139)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 203)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 235)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 100)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 132)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 164)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 196)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 140)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 172)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 204)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 236)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 101)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 133)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 165)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 197)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 229)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 173)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 205)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 237)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 134)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 166)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 198)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 230)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 142)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 174)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 206)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 238)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 103)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 135)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 167)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 199)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 143)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 175)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 207)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*16) + 239)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 196)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 4)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 588)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 12)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 16)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 980)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 20)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1176)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 24)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1372)] = max((conv2d_nchw_1[(i1.inner + 14)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 28)]), 0f32)
}
}
}
@@ -1004,7 +997,7 @@ 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: 0.371 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.321 ms
</pre></div>
</div>
</div>
@@ -1033,36 +1026,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=8)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=8)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1082,12 +1075,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+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=98)
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=4)
+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=64)
+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=98)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1107,430 +1100,456 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[16];
+ __shared__ float pad_temp_shared[392];
+ __shared__ float kernel_shared[256];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- 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[14] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 90)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 188)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 286)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) & 7) * 9)) + (ry_outer_outer * 3))];
+ if (((int)threadIdx.x) < 60) {
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 4) & 7) * 9)) + (ry_outer_outer * 3))];
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 128)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 160)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 192)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 224)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 168)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 200)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 232)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 129)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 161)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 193)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 169)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 201)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 233)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 130)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 162)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 194)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 226)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 170)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 202)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 234)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 131)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 163)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 195)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 227)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 203)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 235)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 132)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 164)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 196)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 172)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 204)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 236)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 133)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 165)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 197)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 229)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 173)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 205)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 237)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 134)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 166)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 198)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 230)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 174)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 206)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 238)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 103)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 135)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 167)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 199)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 175)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 207)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 239)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 91)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 189)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 287)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
+ if (((int)threadIdx.x) < 60) {
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 4) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 128)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 160)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 192)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 224)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 168)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 200)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 232)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 129)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 161)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 193)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 169)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 201)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 233)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 130)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 162)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 194)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 226)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 170)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 202)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 234)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 131)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 163)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 195)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 227)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 203)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 235)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 132)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 164)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 196)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 172)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 204)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 236)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 133)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 165)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 197)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 229)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 173)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 205)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 237)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 134)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 166)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 198)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 230)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 174)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 206)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 238)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 103)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 135)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 167)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 199)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 175)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 207)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 239)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 92)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 190)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + 288)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
+ if (((int)threadIdx.x) < 60) {
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) >> 3) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 4) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 128)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 160)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 192)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 224)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 168)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 200)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 232)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 129)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 161)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 193)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 169)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 201)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 233)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 130)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 162)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 194)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 226)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 170)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 202)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 234)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 131)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 163)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 195)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 227)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 203)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 235)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 132)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 164)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 196)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 172)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 204)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 236)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 133)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 165)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 197)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 229)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 173)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 205)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 237)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 134)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 166)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 198)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 230)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 174)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 206)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 238)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 103)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 135)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 167)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 199)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 175)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 207)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 16) + 239)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 196)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 4)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 588)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 12)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 8)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 980)] = max((conv2d_nchw[(i1_inner + 10)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 20)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1176)] = max((conv2d_nchw[(i1_inner + 12)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 24)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1372)] = max((conv2d_nchw[(i1_inner + 14)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 28)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1567,7 +1586,7 @@ 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 12.949 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 28.171 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 9cb742575..9e386773d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.0574 10.0510 10.1011 10.0202 0.0333
+ 9.8635 9.8866 9.8979 9.8059 0.0410
</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 df377342b..bd8f99294 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 754.1807 753.9919 755.3020 753.2483 0.8490
+ 760.4743 760.4410 760.8218 760.1602 0.2711
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.035 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.008 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 b137c37d0..b6a90e146 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,30 +625,103 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
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, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
+ {
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 16) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
+ for (i.inner: int32, 0, 32) {
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_2: int32 = ((i.outer.inner*512) + (i.inner*16))
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_4: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+ compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -686,7 +759,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.505 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.705 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 761580091..d480cdef7 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.688</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.154</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,7 +336,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:45.653</p></td>
+<td><p>00:46.120</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index b8a250863..948676c6b 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 175.24/175.24 result: MeasureResult(costs=(0.0013210377111111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.035792112350464, timestamp=1659740547.466681) [('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: 0.00/175.24 result: Traceback (most recent call last):
+No: 9 GFLOPS: 203.60/203.60 result: MeasureResult(costs=(0.001137045511111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0944693088531494, timestamp=1659968293.8274136) [('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: 0.00/203.60 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 259.84/259.84 result: MeasureResult(costs=(0.0008909375966850829,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4841654300689697, timestamp=1659740548.388527) [('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: 0.00/259.84 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.06/260.06 result: MeasureResult(costs=(0.0008901913093922652,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.786071538925171, timestamp=1659968294.7591627) [('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: 0.00/260.06 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/259.84 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.06 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/259.84 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.06 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.45/259.84 result: MeasureResult(costs=(0.042476408,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.842756748199463, timestamp=1659740552.940398) [('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: 3.34/259.84 result: MeasureResult(costs=(0.06939392125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.545986652374268, timestamp=1659740554.176307) [('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: 0.00/259.84 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.29/260.06 result: MeasureResult(costs=(0.04377531925,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8445255756378174, timestamp=1659968299.3311553) [('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: 3.34/260.06 result: MeasureResult(costs=(0.06939442074999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.597178220748901, timestamp=1659968300.5865803) [('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: 0.00/260.06 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/259.84 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: 25.97/259.84 result: MeasureResult(costs=(0.008912814833333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1480615139007568, timestamp=1659740565.1115236) [('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: 0.00/259.84 result: Traceback (most recent call last):
+No: 18 GFLOPS: 27.09/260.06 result: MeasureResult(costs=(0.008544821499999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3186297416687012, timestamp=1659968311.6763117) [('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: 0.00/260.06 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/259.84 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.06 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001219
+Time cost of this operator: 0.001217
</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 481b85837..300d3ec2a 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.0 98.725 (1, 2, 10, 10, 3) 2 1 [311.0]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.026 0.961 (1, 6, 10, 10) 1 1 [3.026]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.991 0.315 (1, 1, 10, 10, 3) 1 1 [0.991]
-Total_time - 315.017 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.713 (1, 2, 10, 10, 3) 2 1 [310.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.071 0.977 (1, 6, 10, 10) 1 1 [3.071]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.975 0.31 (1, 1, 10, 10, 3) 1 1 [0.975]
+Total_time - 314.346 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 90.312 97.058 (1, 6, 10, 10, 1) 2 1 [90.312]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.784 1.917 (1, 6, 10, 10) 1 1 [1.784]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 1.025 (1, 1, 10, 10, 3) 1 1 [0.954]
-Total_time - 93.05 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 118.4 97.711 (1, 6, 10, 10, 1) 2 1 [118.4]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.82 1.502 (1, 6, 10, 10) 1 1 [1.82]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.787 (1, 1, 10, 10, 3) 1 1 [0.954]
+Total_time - 121.174 - - - - -
</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 c26be7388..4c346f384 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmptdcmv1sf/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp6nerfeb0/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmptdcmv1sf/images/target contains 8144 images
-/tmp/tmptdcmv1sf/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/tmp6nerfeb0/images/target contains 8144 images
+/tmp/tmp6nerfeb0/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2268 - accuracy: 0.9224 - val_loss: 0.1540 - val_accuracy: 0.9498
+328/328 - 55s - loss: 0.2112 - accuracy: 0.9270 - val_loss: 0.1379 - val_accuracy: 0.9566
Epoch 2/3
-328/328 - 52s - loss: 0.1022 - accuracy: 0.9605 - val_loss: 0.1117 - val_accuracy: 0.9675
+328/328 - 52s - loss: 0.0966 - accuracy: 0.9631 - val_loss: 0.1143 - val_accuracy: 0.9630
Epoch 3/3
-328/328 - 52s - loss: 0.0698 - accuracy: 0.9733 - val_loss: 0.1227 - val_accuracy: 0.9653
+328/328 - 52s - loss: 0.0644 - accuracy: 0.9754 - val_loss: 0.1292 - val_accuracy: 0.9596
-<keras.callbacks.History object at 0x7f3b9a76f910>
+<keras.callbacks.History object at 0x7f5e925ec1d0>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 44.392 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 7.304 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 5422fdd82..6f6ffaeaf 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:37.131</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:01.022</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:44.392</p></td>
+<td><p>05:07.304</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>00:41.724</p></td>
+<td><p>00:42.474</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.730</p></td>
+<td><p>00:07.889</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.284</p></td>
+<td><p>00:03.353</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index f017dc7b4..3dfbd6471 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.374</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:41.993</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</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>00:30.059</p></td>
+<td><p>00:30.600</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>00:07.857</p></td>
+<td><p>00:09.872</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>00:02.451</p></td>
+<td><p>00:01.513</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>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 8a0c83b34..f6ebe568c 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f3b1b6f3ef0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f5e22165d40>
</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 8e6889b6f..580926b59 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.123</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.227</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,23 +336,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.873</p></td>
+<td><p>00:01.954</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>00:01.029</p></td>
+<td><p>00:01.014</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>00:00.525</p></td>
+<td><p>00:00.545</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>00:00.513</p></td>
+<td><p>00:00.530</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>00:00.099</p></td>
+<td><p>00:00.102</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -360,7 +360,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index c60ef0cf2..fc278cf00 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpqp_i2j13/input0.cc'\nsource_filename = \"/tmp/tmpqp_i2j13/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/tmpshpsgnys/input0.cc'\nsource_filename = \"/tmp/tmpshpsgnys/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index aa2238b85..3153785d7 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,17 +224,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/objects.inv b/docs/objects.inv
index f069e1be1..8fe91b841 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/doxygen/builtin_8h.html b/docs/reference/api/doxygen/builtin_8h.html
index 6299190b8..d6b210547 100644
--- a/docs/reference/api/doxygen/builtin_8h.html
+++ b/docs/reference/api/doxygen/builtin_8h.html
@@ -337,6 +337,9 @@ Functions</h2></td></tr>
<tr class="memitem:a0b3d8f41abba4b7dd4a9af8ec2f9acba"><td class="memItemLeft" align="right" valign="top">const Op & </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1builtin.html#a0b3d8f41abba4b7dd4a9af8ec2f9acba">tvm::tir::builtin::assume</a> ()</td></tr>
<tr class="memdesc:a0b3d8f41abba4b7dd4a9af8ec2f9acba"><td class="mdescLeft"> </td><td class="mdescRight">Provide a true statement that can be used for simplifications. <a href="namespacetvm_1_1tir_1_1builtin.html#a0b3d8f41abba4b7dd4a9af8ec2f9acba">More...</a><br /></td></tr>
<tr class="separator:a0b3d8f41abba4b7dd4a9af8ec2f9acba"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a77a72a2e21fe0ea2118479924b4fb877"><td class="memItemLeft" align="right" valign="top">const Op & </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877">tvm::tir::builtin::undef</a> ()</td></tr>
+<tr class="memdesc:a77a72a2e21fe0ea2118479924b4fb877"><td class="mdescLeft"> </td><td class="mdescRight">Returns an initialized but arbitrary value. <a href="namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877">More...</a><br /></td></tr>
+<tr class="separator:a77a72a2e21fe0ea2118479924b4fb877"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
<div class="textblock"><p>TIR builtin intrinsics. </p>
diff --git a/docs/reference/api/doxygen/builtin_8h_source.html b/docs/reference/api/doxygen/builtin_8h_source.html
index 1b435a625..05f28633e 100644
--- a/docs/reference/api/doxygen/builtin_8h_source.html
+++ b/docs/reference/api/doxygen/builtin_8h_source.html
@@ -66,9 +66,9 @@ $(function() {
<div class="title">builtin.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="builtin_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more con [...]
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1cad28cfc7b69fd8745e12a4f0024d6942a"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1cad28cfc7b69fd8745e12a4f0024d6942a">tvm::tir::builtin::kArrNDim</a></div><div class="ttdef"><b>Definition:</b> builtin.h:739</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca0b8af30aa268164148d5bfe1d8c2ba54"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca0b8af30aa268164148d5bfe1d8c2ba54">tvm::tir::builtin::kArrAddr</a></div><div class="ttdef"><b>Definition:</b> builtin.h:735</div></div>
+<a href="builtin_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more con [...]
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1cad28cfc7b69fd8745e12a4f0024d6942a"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1cad28cfc7b69fd8745e12a4f0024d6942a">tvm::tir::builtin::kArrNDim</a></div><div class="ttdef"><b>Definition:</b> builtin.h:747</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca0b8af30aa268164148d5bfe1d8c2ba54"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca0b8af30aa268164148d5bfe1d8c2ba54">tvm::tir::builtin::kArrAddr</a></div><div class="ttdef"><b>Definition:</b> builtin.h:743</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a925a45e5bb05e0cbf2daf2ffdbdcf53a"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a925a45e5bb05e0cbf2daf2ffdbdcf53a">tvm::tir::builtin::tvm_storage_sync</a></div><div class="ttdeci">const Op & tvm_storage_sync()</div><div class="ttdoc">See pseudo code. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a15c5e0e0478e0ebff91690f60992cf3f"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a15c5e0e0478e0ebff91690f60992cf3f">tvm::tir::builtin::tvm_stack_alloca</a></div><div class="ttdeci">const Op & tvm_stack_alloca()</div><div class="ttdoc">See pesudo code. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_aa1d19e758595200998a4e1ea39767b6b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#aa1d19e758595200998a4e1ea39767b6b">tvm::tir::builtin::tvm_thread_allreduce</a></div><div class="ttdeci">const Op & tvm_thread_allreduce()</div><div class="ttdoc">See pesudo code. </div></div>
@@ -78,9 +78,10 @@ $(function() {
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a83892dca19e44a96752625c65c38d645"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a83892dca19e44a96752625c65c38d645">tvm::tir::builtin::call_llvm_intrin</a></div><div class="ttdeci">const Op & call_llvm_intrin()</div><div class="ttdoc">Call an LLVM intrinsic with a given intrinsic id and signature from the types of args in the runtime ...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a772fb68f083e71e635c50bb503903f22"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a772fb68f083e71e635c50bb503903f22">tvm::tir::builtin::mma_store</a></div><div class="ttdeci">const Op & mma_store()</div><div class="ttdoc">tvm intrinsic for storing the result of PTX MMA into a destination pointer. For example, if each thread in a warp of size 32 has 4 elements from the result of m16xn8xk16 MMA in its registers, [...]
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1cabf798b873c868b7d77ced30c9907037d"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1cabf798b873c868b7d77ced30c9907037d">tvm::tir::builtin::kArrDeviceType</a></div><div class="ttdef"><b>Definition:</b> builtin.h:745</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1cabf798b873c868b7d77ced30c9907037d"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1cabf798b873c868b7d77ced30c9907037d">tvm::tir::builtin::kArrDeviceType</a></div><div class="ttdef"><b>Definition:</b> builtin.h:753</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a1e15b04fe89f7899e09e528946aa5bb4"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a1e15b04fe89f7899e09e528946aa5bb4">tvm::tir::builtin::fma</a></div><div class="ttdeci">const Op & fma()</div><div class="ttdoc">Fused multiply add. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a8e3504415c78f3f8fd719a21e5280b38"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a8e3504415c78f3f8fd719a21e5280b38">tvm::tir::builtin::call_llvm_pure_intrin</a></div><div class="ttdeci">const Op & call_llvm_pure_intrin()</div><div class="ttdoc">Call an LLVM pure intrinsic with a given intrinsic id and signature from the types of args in the run...</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a77a72a2e21fe0ea2118479924b4fb877"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877">tvm::tir::builtin::undef</a></div><div class="ttdeci">const Op & undef()</div><div class="ttdoc">Returns an initialized but arbitrary value. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ab4a648f6e7451af295688f243a215cd7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ab4a648f6e7451af295688f243a215cd7">tvm::tir::builtin::atomic_add</a></div><div class="ttdeci">const Op & atomic_add()</div><div class="ttdoc">atomic add instruction, corresponding e.g. to atomicAdd in CUDA </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ac8e7bc86b8fa81453291ae5299062001"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ac8e7bc86b8fa81453291ae5299062001">tvm::tir::builtin::tvm_global_barrier_kinit</a></div><div class="ttdeci">const Op & tvm_global_barrier_kinit()</div><div class="ttdoc">Initialize the global barrier. Call this at beginning of kernel that need global barrier. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a3131992ea9acd964fb7d3ca782d74805"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a3131992ea9acd964fb7d3ca782d74805">tvm::tir::builtin::tvm_call_cpacked_lowered</a></div><div class="ttdeci">const Op & tvm_call_cpacked_lowered()</div><div class="ttdoc">Lowered version of call c-packed, the space of value and type codes are explicitly allocated...</div></div>
@@ -88,29 +89,29 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ae0470bd69bb03047aae4cb52e1e6e337"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ae0470bd69bb03047aae4cb52e1e6e337">tvm::tir::builtin::tvm_warp_shuffle_up</a></div><div class="ttdeci">const Op & tvm_warp_shuffle_up()</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ac54288cc9f1fee8c26db9bd87ac320ee"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ac54288cc9f1fee8c26db9bd87ac320ee">tvm::tir::builtin::tvm_call_trace_packed</a></div><div class="ttdeci">const Op & tvm_call_trace_packed()</div><div class="ttdoc">See pesudo code. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_afc81da8cbcd7f34ec5e1e80d837ca265"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#afc81da8cbcd7f34ec5e1e80d837ca265">tvm::tir::builtin::tvm_store_matrix_sync</a></div><div class="ttdeci">const Op & tvm_store_matrix_sync()</div><div class="ttdoc">tvm intrinsic for tensor core store operators. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca96e7b6492b5b174219cf60e19af0857c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca96e7b6492b5b174219cf60e19af0857c">tvm::tir::builtin::kArrStrides</a></div><div class="ttdef"><b>Definition:</b> builtin.h:738</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca96e7b6492b5b174219cf60e19af0857c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca96e7b6492b5b174219cf60e19af0857c">tvm::tir::builtin::kArrStrides</a></div><div class="ttdef"><b>Definition:</b> builtin.h:746</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ac4887bd93ad67619ad290a33e2bdd340"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ac4887bd93ad67619ad290a33e2bdd340">tvm::tir::builtin::call_spirv_pure_glsl450</a></div><div class="ttdeci">const Op & call_spirv_pure_glsl450()</div><div class="ttdoc">Call an SPIRV pure GLSL450 intrinsic. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a6be181be34fba13d129aadc6c9a23f73"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a6be181be34fba13d129aadc6c9a23f73">tvm::tir::builtin::tvm_thread_context</a></div><div class="ttdeci">const Op & tvm_thread_context()</div><div class="ttdoc">See pesudo code Mark the content as thread local context, can get optimized by only call the call onc...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a700b7018f2c1f1fba8b4e28f264d8bbb"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a700b7018f2c1f1fba8b4e28f264d8bbb">tvm::tir::builtin::address_of</a></div><div class="ttdeci">const Op & address_of()</div><div class="ttdoc">Returns the address of an element in the buffer (see pseudocode below). </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a091ef99dc63f6945588dbb81c968ca15"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a091ef99dc63f6945588dbb81c968ca15">tvm::tir::builtin::bitwise_not</a></div><div class="ttdeci">const Op & bitwise_not()</div><div class="ttdoc">Bitwise not operator. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1cafdb925cdf50f17a2b96c7ac4faefa1fb"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1cafdb925cdf50f17a2b96c7ac4faefa1fb">tvm::tir::builtin::kArrByteOffset</a></div><div class="ttdef"><b>Definition:</b> builtin.h:743</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1cafdb925cdf50f17a2b96c7ac4faefa1fb"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1cafdb925cdf50f17a2b96c7ac4faefa1fb">tvm::tir::builtin::kArrByteOffset</a></div><div class="ttdef"><b>Definition:</b> builtin.h:751</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a0c2ebdcec34d7c79dc8480e5dab8547a"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a0c2ebdcec34d7c79dc8480e5dab8547a">tvm::tir::builtin::q_multiply_shift</a></div><div class="ttdeci">const Op & q_multiply_shift()</div><div class="ttdoc">Execute a multiplication between two Q-numbers x and y followed by a right shift s The default roundi...</div></div>
<div class="ttc" id="ir_2op_8h_html"><div class="ttname"><a href="ir_2op_8h.html">op.h</a></div><div class="ttdoc">Primitive operators(builtin intrinsics) and registry for them. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a7ed64a9fb0a7f575fc63e1e0395e96a6"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a7ed64a9fb0a7f575fc63e1e0395e96a6">tvm::tir::builtin::vectorlow</a></div><div class="ttdeci">const Op & vectorlow()</div><div class="ttdoc">Get the low-level half of the vector. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a0cbd267877168afd5bbea35f0e5d70fe"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a0cbd267877168afd5bbea35f0e5d70fe">tvm::tir::builtin::tvm_mma_sync</a></div><div class="ttdeci">const Op & tvm_mma_sync()</div><div class="ttdoc">tvm intrinsic for tensor core mma_sync operators. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca344dc1f419339b81024d4d3628083a1e"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca344dc1f419339b81024d4d3628083a1e">tvm::tir::builtin::kArrTypeBits</a></div><div class="ttdef"><b>Definition:</b> builtin.h:741</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca344dc1f419339b81024d4d3628083a1e"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca344dc1f419339b81024d4d3628083a1e">tvm::tir::builtin::kArrTypeBits</a></div><div class="ttdef"><b>Definition:</b> builtin.h:749</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a7b555bc5cca2f5e7b26c1037bc0001ce"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a7b555bc5cca2f5e7b26c1037bc0001ce">tvm::tir::builtin::reinterpret</a></div><div class="ttdeci">const Op & reinterpret()</div><div class="ttdoc">Reinterpret the value using the target type. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ae79143f4df15683d7ee25c0b958e2189"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ae79143f4df15683d7ee25c0b958e2189">tvm::tir::builtin::ptx_ldmatrix</a></div><div class="ttdeci">const Op & ptx_ldmatrix()</div><div class="ttdoc">tvm intrinsic for ptx load matrix from shared memory. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ae2add6e324d391782d367360a68ccf51"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ae2add6e324d391782d367360a68ccf51">tvm::tir::builtin::call_pure_extern</a></div><div class="ttdeci">const Op & call_pure_extern()</div><div class="ttdoc">Call an pure extern C function with given name and signature from the types of args in the runtime en...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ae52feb3e7828262a1b8a31062642ae36"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ae52feb3e7828262a1b8a31062642ae36">tvm::tir::builtin::texture2d_load</a></div><div class="ttdeci">const Op & texture2d_load()</div><div class="ttdoc">Load from texture 2d memory. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a2172690dd21d7fd50a4fd4d696ea7bb2"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a2172690dd21d7fd50a4fd4d696ea7bb2">tvm::tir::builtin::popcount</a></div><div class="ttdeci">const Op & popcount()</div><div class="ttdoc">Popcount. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca0c960782c20a4f16cfe203c516760b00"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca0c960782c20a4f16cfe203c516760b00">tvm::tir::builtin::kArrTypeLanes</a></div><div class="ttdef"><b>Definition:</b> builtin.h:742</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca0c960782c20a4f16cfe203c516760b00"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca0c960782c20a4f16cfe203c516760b00">tvm::tir::builtin::kArrTypeLanes</a></div><div class="ttdef"><b>Definition:</b> builtin.h:750</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a2c13c6e4b2f92e17f357665f9f11736c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a2c13c6e4b2f92e17f357665f9f11736c">tvm::tir::builtin::tvm_call_packed</a></div><div class="ttdeci">const Op & tvm_call_packed()</div><div class="ttdoc">See pesudo code. </div></div>
<div class="ttc" id="tir_2expr_8h_html"><div class="ttname"><a href="tir_2expr_8h.html">expr.h</a></div><div class="ttdoc">TIR expressions. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca4d4a5d54434514fd8b0ce57160059c92"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca4d4a5d54434514fd8b0ce57160059c92">tvm::tir::builtin::kArrKindBound_</a></div><div class="ttdef"><b>Definition:</b> builtin.h:746</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca4d4a5d54434514fd8b0ce57160059c92"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca4d4a5d54434514fd8b0ce57160059c92">tvm::tir::builtin::kArrKindBound_</a></div><div class="ttdef"><b>Definition:</b> builtin.h:754</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a21d1f0395dca5af4a90cdb42c1d1d154"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a21d1f0395dca5af4a90cdb42c1d1d154">tvm::tir::builtin::likely</a></div><div class="ttdeci">const Op & likely()</div><div class="ttdoc">Marks a condition is likely going to happen. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a23003bd9331efaa58d8420529ea96c0b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a23003bd9331efaa58d8420529ea96c0b">tvm::tir::builtin::tvm_struct_get</a></div><div class="ttdeci">const Op & tvm_struct_get()</div><div class="ttdoc">See pesudo code. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca779c07403e11f671e936ec2813ce2304"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca779c07403e11f671e936ec2813ce2304">tvm::tir::builtin::kTVMValueContent</a></div><div class="ttdef"><b>Definition:</b> builtin.h:748</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca779c07403e11f671e936ec2813ce2304"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca779c07403e11f671e936ec2813ce2304">tvm::tir::builtin::kTVMValueContent</a></div><div class="ttdef"><b>Definition:</b> builtin.h:756</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a28f99e6dd767482765b854ee9fc71f2c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a28f99e6dd767482765b854ee9fc71f2c">tvm::tir::builtin::tvm_stack_make_array</a></div><div class="ttdeci">const Op & tvm_stack_make_array()</div><div class="ttdoc">Allocate a NDArray(DLTensor) on stack, return the handle. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a543f1fc334d2bc830add972895a03f17"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a543f1fc334d2bc830add972895a03f17">tvm::tir::builtin::prefetch</a></div><div class="ttdeci">const Op & prefetch()</div><div class="ttdoc">Prefetch a cacheline. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a92624d2aa5c435cd7a0ea8efb698a115"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a92624d2aa5c435cd7a0ea8efb698a115">tvm::tir::builtin::tvm_throw_last_error</a></div><div class="ttdeci">const Op & tvm_throw_last_error()</div><div class="ttdoc">See pesudo code. </div></div>
@@ -120,10 +121,10 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a0aee850e8e98b29fbcc8f269f5136e92"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a0aee850e8e98b29fbcc8f269f5136e92">tvm::tir::builtin::mem_copy</a></div><div class="ttdeci">const Op & mem_copy()</div><div class="ttdoc">Copy 1d memory from source to destination Same semantics as memcpy(destination, source, size) Allows for device specific implementations e.g. direct memory access (DMA) </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_abd540cb73407771ecfb4f78722ce5a1b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#abd540cb73407771ecfb4f78722ce5a1b">tvm::tir::builtin::tvm_stack_make_shape</a></div><div class="ttdeci">const Op & tvm_stack_make_shape()</div><div class="ttdoc">Allocate a shape tuple on stack, return the handle. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ae741e67259cd4b844a8934f2e2704adc"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ae741e67259cd4b844a8934f2e2704adc">tvm::tir::builtin::if_then_else</a></div><div class="ttdeci">const Op & if_then_else()</div><div class="ttdoc">Same as select, used for unsafe memory access. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1caa73457ed97931251f1762cb319adc858"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1caa73457ed97931251f1762cb319adc858">tvm::tir::builtin::kTVMValueKindBound_</a></div><div class="ttdef"><b>Definition:</b> builtin.h:749</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1caa73457ed97931251f1762cb319adc858"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1caa73457ed97931251f1762cb319adc858">tvm::tir::builtin::kTVMValueKindBound_</a></div><div class="ttdef"><b>Definition:</b> builtin.h:757</div></div>
<div class="ttc" id="classtvm_1_1Op_html"><div class="ttname"><a href="classtvm_1_1Op.html">tvm::Op</a></div><div class="ttdoc">Managed reference class to OpNode. </div><div class="ttdef"><b>Definition:</b> op.h:165</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a7eaa1b0b7d7cb550f6a7eaf5efe8d493"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a7eaa1b0b7d7cb550f6a7eaf5efe8d493">tvm::tir::builtin::ptx_cp_async</a></div><div class="ttdeci">const Op & ptx_cp_async()</div><div class="ttdoc">tvm intrinsics for ptx async copy from global to shared memory </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca57f69fd3d141caaa7e2e72fda7d6a1da"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca57f69fd3d141caaa7e2e72fda7d6a1da">tvm::tir::builtin::kArrShape</a></div><div class="ttdef"><b>Definition:</b> builtin.h:737</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca57f69fd3d141caaa7e2e72fda7d6a1da"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca57f69fd3d141caaa7e2e72fda7d6a1da">tvm::tir::builtin::kArrShape</a></div><div class="ttdef"><b>Definition:</b> builtin.h:745</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a3343bb32988cda13d3050e8fc2a75a78"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a3343bb32988cda13d3050e8fc2a75a78">tvm::tir::builtin::ptx_mma_sp</a></div><div class="ttdeci">const Op & ptx_mma_sp()</div><div class="ttdoc">tvm intrinsic for sparse tensor core ptx instructions. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_afc4086a245ded9076de226ae802ced32"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#afc4086a245ded9076de226ae802ced32">tvm::tir::builtin::tvm_warp_activemask</a></div><div class="ttdeci">const Op & tvm_warp_activemask()</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a668eaad07b6c46238f2bf758e61b58a5"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a668eaad07b6c46238f2bf758e61b58a5">tvm::tir::builtin::call_extern</a></div><div class="ttdeci">const Op & call_extern()</div><div class="ttdoc">Call an extern C function with given name and signature from the types of args in the runtime environ...</div></div>
@@ -136,7 +137,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a6aeb24a28d19cdc60e4e1fa7b420d7fd"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a6aeb24a28d19cdc60e4e1fa7b420d7fd">tvm::tir::builtin::tvm_static_handle</a></div><div class="ttdeci">const Op & tvm_static_handle()</div><div class="ttdoc">Create a function local static handle that iniitalizes to nullptr. can be used to cache function loca...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a23897d81faa46ac29ab0d6d8fc618707"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a23897d81faa46ac29ab0d6d8fc618707">tvm::tir::builtin::tvm_check_return</a></div><div class="ttdeci">const Op & tvm_check_return()</div><div class="ttdoc">Checks the return value of another call is correct or returns a given value. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a0b3d8f41abba4b7dd4a9af8ec2f9acba"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a0b3d8f41abba4b7dd4a9af8ec2f9acba">tvm::tir::builtin::assume</a></div><div class="ttdeci">const Op & assume()</div><div class="ttdoc">Provide a true statement that can be used for simplifications. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1c">tvm::tir::builtin::TVMStructFieldKind</a></div><div class="ttdeci">TVMStructFieldKind</div><div class="ttdoc">The kind of structure field info used in intrinsic. </div><div class="ttdef"><b>Definition:</b> builtin.h:733</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1c">tvm::tir::builtin::TVMStructFieldKind</a></div><div class="ttdeci">TVMStructFieldKind</div><div class="ttdoc">The kind of structure field info used in intrinsic. </div><div class="ttdef"><b>Definition:</b> builtin.h:741</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a0e633f53c50e14d7e2fc07636a223309"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a0e633f53c50e14d7e2fc07636a223309">tvm::tir::builtin::bitwise_and</a></div><div class="ttdeci">const Op & bitwise_and()</div><div class="ttdoc">Bitwise and operator. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a6f53be295396c301082696ca0c113501"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a6f53be295396c301082696ca0c113501">tvm::tir::builtin::isnan</a></div><div class="ttdeci">const Op & isnan()</div><div class="ttdoc">Check if value is nan. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a21346695611f032cadc3fad6615fe63b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a21346695611f032cadc3fad6615fe63b">tvm::tir::builtin::ptx_commit_group</a></div><div class="ttdeci">const Op & ptx_commit_group()</div><div class="ttdoc">tvm intrinsics for ptx async copy commit and wait. </div></div>
@@ -149,10 +150,10 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a322ae63444ed4e5fcf7247aa93f8bb7c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a322ae63444ed4e5fcf7247aa93f8bb7c">tvm::tir::builtin::large_uint_imm</a></div><div class="ttdeci">const Op & large_uint_imm()</div><div class="ttdoc">See pesudo code. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a307667c449c54cef747d781771f79bab"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a307667c449c54cef747d781771f79bab">tvm::tir::builtin::mma_fill</a></div><div class="ttdeci">const Op & mma_fill()</div><div class="ttdoc">tvm intrinsic for zero-initalizing an MMA accumulation registor. For example, if each thread in a war...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a21c2ad8b095dcbefa786394981ea0b71"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a21c2ad8b095dcbefa786394981ea0b71">tvm::tir::builtin::tvm_context_id</a></div><div class="ttdeci">const Op & tvm_context_id()</div><div class="ttdoc">Return a unique context id, used for hint of workspace separation. Different context id ganrantees no...</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca9076fb1a58386bac2e0f1fdae9cab844"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca9076fb1a58386bac2e0f1fdae9cab844">tvm::tir::builtin::kArrData</a></div><div class="ttdef"><b>Definition:</b> builtin.h:736</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca9076fb1a58386bac2e0f1fdae9cab844"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca9076fb1a58386bac2e0f1fdae9cab844">tvm::tir::builtin::kArrData</a></div><div class="ttdef"><b>Definition:</b> builtin.h:744</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a26472adf05d821f1929cfbc02bc3c231"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a26472adf05d821f1929cfbc02bc3c231">tvm::tir::builtin::shift_left</a></div><div class="ttdeci">const Op & shift_left()</div><div class="ttdoc">Left shift. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a9603510b7eff067c253eb340310c2996"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a9603510b7eff067c253eb340310c2996">tvm::tir::builtin::nd_mem_alloc_with_scope</a></div><div class="ttdeci">const Op & nd_mem_alloc_with_scope()</div><div class="ttdoc">Create an Nd memory allocation with storage scope. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca5ce842cabb26975681dd561c5132af1b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca5ce842cabb26975681dd561c5132af1b">tvm::tir::builtin::kArrTypeCode</a></div><div class="ttdef"><b>Definition:</b> builtin.h:740</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_ad3b90c881b67ebe8e8fe68f14143bb1ca5ce842cabb26975681dd561c5132af1b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#ad3b90c881b67ebe8e8fe68f14143bb1ca5ce842cabb26975681dd561c5132af1b">tvm::tir::builtin::kArrTypeCode</a></div><div class="ttdef"><b>Definition:</b> builtin.h:748</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_aa6e23eac98abb8378b9837011a5c04b5"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#aa6e23eac98abb8378b9837011a5c04b5">tvm::tir::builtin::tvm_call_trace_packed_lowered</a></div><div class="ttdeci">const Op & tvm_call_trace_packed_lowered()</div><div class="ttdoc">Lowered version of trace intrinsic, the space of value and type codes are explicitly allocated...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_aa5b0e90771b35d78b6c07c0054abe023"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#aa5b0e90771b35d78b6c07c0054abe023">tvm::tir::builtin::isnullptr</a></div><div class="ttdeci">const Op & isnullptr()</div><div class="ttdoc">See pesudo code. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_aed0dcc804c2d1b939969c9e48aa448f9"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#aed0dcc804c2d1b939969c9e48aa448f9">tvm::tir::builtin::ptx_wait_group</a></div><div class="ttdeci">const Op & ptx_wait_group()</div></div>
diff --git a/docs/reference/api/doxygen/data__layout_8h_source.html b/docs/reference/api/doxygen/data__layout_8h_source.html
index 0501efd5b..f713bb376 100644
--- a/docs/reference/api/doxygen/data__layout_8h_source.html
+++ b/docs/reference/api/doxygen/data__layout_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">data_layout.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="data__layout_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or mor [...]
+<a href="data__layout_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or mor [...]
<div class="ttc" id="classtvm_1_1tir_1_1Layout_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Layout.html">tvm::tir::Layout</a></div><div class="ttdoc">Managed reference to LayoutNode. </div><div class="ttdef"><b>Definition:</b> data_layout.h:123</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Layout_html_a772258f23824fe6488bc3a8ce8ff1b80"><div class="ttname"><a href="classtvm_1_1tir_1_1Layout.html#a772258f23824fe6488bc3a8ce8ff1b80">tvm::tir::Layout::IndexOf</a></div><div class="ttdeci">int32_t IndexOf(const LayoutAxis &axis) const</div><div class="ttdoc">return the index of the input axis. If it is not found in the layout or the layout is undefined...</div><div class="ttdef"><b>Definition:</b> data_layout.h:224</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Layout_html_a35389f5ca857483ea65756bb2ceaa944"><div class="ttname"><a href="classtvm_1_1tir_1_1Layout.html#a35389f5ca857483ea65756bb2ceaa944">tvm::tir::Layout::Equals</a></div><div class="ttdeci">bool Equals(const Layout &rhs) const</div><div class="ttdoc">Whether the two layouts are equal. </div><div class="ttdef"><b>Definition:</b> data_layout.h:276</div></div>
@@ -78,6 +78,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1LayoutNode_html_a4287f43c0ae133205d9803f4fadc3d88"><div class="ttname"><a href="classtvm_1_1tir_1_1LayoutNode.html#a4287f43c0ae133205d9803f4fadc3d88">tvm::tir::LayoutNode::axes</a></div><div class="ttdeci">Array< tir::IterVar > axes</div><div class="ttdoc">specify each axis of the layout, in which the variable name is the name of the axis. The IterVar&#39;s extent indicates the size of the axis, it is a variable for a primal axis, but a c [...]
<div class="ttc" id="classtvm_1_1tir_1_1VarNode_html_aefe69c9361d4ab7282a9c07efebe4414"><div class="ttname"><a href="classtvm_1_1tir_1_1VarNode.html#aefe69c9361d4ab7282a9c07efebe4414">tvm::tir::VarNode::name_hint</a></div><div class="ttdeci">String name_hint</div><div class="ttdoc">The hint to the variable name. </div><div class="ttdef"><b>Definition:</b> var.h:53</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1IterVar_html"><div class="ttname"><a href="classtvm_1_1tir_1_1IterVar.html">tvm::tir::IterVar</a></div><div class="ttdoc">Iteration Variable, represents an iteration over an integer interval. </div><div class="ttdef"><b>Definition:</b> var.h:301</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a77a72a2e21fe0ea2118479924b4fb877"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877">tvm::tir::builtin::undef</a></div><div class="ttdeci">const Op & undef()</div><div class="ttdoc">Returns an initialized but arbitrary value. </div></div>
<div class="ttc" id="namespacestd_html"><div class="ttname"><a href="namespacestd.html">std</a></div><div class="ttdef"><b>Definition:</b> loop_state.h:456</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="tir_2op_8h_html"><div class="ttname"><a href="tir_2op_8h.html">op.h</a></div><div class="ttdoc">Common operators defined for Expr. </div></div>
diff --git a/docs/reference/api/doxygen/namespacemembers_func_p.html b/docs/reference/api/doxygen/namespacemembers_func_p.html
index 7c33a5248..803915cb0 100644
--- a/docs/reference/api/doxygen/namespacemembers_func_p.html
+++ b/docs/reference/api/doxygen/namespacemembers_func_p.html
@@ -67,12 +67,12 @@ $(function() {
<li>PackImportsToLLVM()
: <a class="el" href="namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6">tvm::codegen</a>
</li>
-<li>pad()
-: <a class="el" href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi</a>
-</li>
<li>Pad()
: <a class="el" href="namespacetvm_1_1topi.html#a97c798d0a0ec20a95d351618b83d5121">tvm::topi</a>
</li>
+<li>pad()
+: <a class="el" href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi</a>
+</li>
<li>parallel_for()
: <a class="el" href="namespacetvm_1_1support.html#a8bf1225e8bb1db575578ca2d645fb23c">tvm::support</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacemembers_func_r.html b/docs/reference/api/doxygen/namespacemembers_func_r.html
index 865e0321a..2993958f5 100644
--- a/docs/reference/api/doxygen/namespacemembers_func_r.html
+++ b/docs/reference/api/doxygen/namespacemembers_func_r.html
@@ -87,6 +87,9 @@ $(function() {
<li>RemoveRPCSessionMask()
: <a class="el" href="namespacetvm_1_1runtime.html#af32398517b6b915361c5716f8e32c16f">tvm::runtime</a>
</li>
+<li>RemoveStandaloneReshapes()
+: <a class="el" href="namespacetvm_1_1relay_1_1transform.html#abf8753e6152a3ce13488eea22827cac9">tvm::relay::transform</a>
+</li>
<li>RemoveUnusedFunctions()
: <a class="el" href="namespacetvm_1_1relay_1_1transform.html#afbbf5f3e5ffb775fafb9c48473dbfa24">tvm::relay::transform</a>
</li>
@@ -129,7 +132,7 @@ $(function() {
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#a4fe43327c4454dd05b6e925577443f49">tvm::tir::transform</a>
</li>
<li>right_shift()
-: <a class="el" href="namespacetvm.html#af49dde9dfdeea62e8ad3a6d8db53de0b">tvm</a>
+: <a class="el" href="namespacetvm.html#ae8ecc0382685a855187bede0c97d93e6">tvm</a>
, <a class="el" href="namespacetvm_1_1topi.html#a8d155306c648c5925352eca1d7b17a60">tvm::topi</a>
</li>
<li>rocblas_batch_matmul()
diff --git a/docs/reference/api/doxygen/namespacemembers_func_s.html b/docs/reference/api/doxygen/namespacemembers_func_s.html
index 1a0b189a7..f7e755cea 100644
--- a/docs/reference/api/doxygen/namespacemembers_func_s.html
+++ b/docs/reference/api/doxygen/namespacemembers_func_s.html
@@ -234,12 +234,12 @@ $(function() {
<li>Specialize()
: <a class="el" href="namespacetvm_1_1tir.html#a69b6f1b0014dc6e7dd390cff746e9782">tvm::tir</a>
</li>
-<li>Split()
-: <a class="el" href="namespacetvm_1_1topi.html#a164125ca6dd5c4b677f72e63ce6b3c21">tvm::topi</a>
-</li>
<li>split()
: <a class="el" href="namespacetvm_1_1topi.html#af4e59b01a5842baf6b47ad3f83731f53">tvm::topi</a>
</li>
+<li>Split()
+: <a class="el" href="namespacetvm_1_1topi.html#a164125ca6dd5c4b677f72e63ce6b3c21">tvm::topi</a>
+</li>
<li>split_sections()
: <a class="el" href="namespacetvm_1_1topi.html#acc643e2ed166fa2ed82a95853e145619">tvm::topi</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacemembers_func_u.html b/docs/reference/api/doxygen/namespacemembers_func_u.html
index c2452427d..e6755b5e3 100644
--- a/docs/reference/api/doxygen/namespacemembers_func_u.html
+++ b/docs/reference/api/doxygen/namespacemembers_func_u.html
@@ -64,8 +64,11 @@ $(function() {
<li>UnCPS()
: <a class="el" href="namespacetvm_1_1relay.html#a1677d450d58078811f52fd70d67db515">tvm::relay</a>
</li>
+<li>undef()
+: <a class="el" href="namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877">tvm::tir::builtin</a>
+</li>
<li>UndefinedVars()
-: <a class="el" href="namespacetvm_1_1tir.html#ae110e02855d8bc12eb8b6f92ed391844">tvm::tir</a>
+: <a class="el" href="namespacetvm_1_1tir.html#a99de316b20c7af2e8b4f06773ee69a5a">tvm::tir</a>
</li>
<li>UnifiedStaticMemoryPlanner()
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#aca44076eb1085d664877596a8b8587d4">tvm::tir::transform</a>
diff --git a/docs/reference/api/doxygen/namespacemembers_p.html b/docs/reference/api/doxygen/namespacemembers_p.html
index eb3b32fd5..33cb466d5 100644
--- a/docs/reference/api/doxygen/namespacemembers_p.html
+++ b/docs/reference/api/doxygen/namespacemembers_p.html
@@ -67,12 +67,12 @@ $(function() {
<li>PackImportsToLLVM()
: <a class="el" href="namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6">tvm::codegen</a>
</li>
-<li>pad()
-: <a class="el" href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi</a>
-</li>
<li>Pad()
: <a class="el" href="namespacetvm_1_1topi.html#a97c798d0a0ec20a95d351618b83d5121">tvm::topi</a>
</li>
+<li>pad()
+: <a class="el" href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi</a>
+</li>
<li>parallel_for()
: <a class="el" href="namespacetvm_1_1support.html#a8bf1225e8bb1db575578ca2d645fb23c">tvm::support</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacemembers_r.html b/docs/reference/api/doxygen/namespacemembers_r.html
index bb51571e8..2ce8d0b5c 100644
--- a/docs/reference/api/doxygen/namespacemembers_r.html
+++ b/docs/reference/api/doxygen/namespacemembers_r.html
@@ -105,6 +105,9 @@ $(function() {
<li>RemoveRPCSessionMask()
: <a class="el" href="namespacetvm_1_1runtime.html#af32398517b6b915361c5716f8e32c16f">tvm::runtime</a>
</li>
+<li>RemoveStandaloneReshapes()
+: <a class="el" href="namespacetvm_1_1relay_1_1transform.html#abf8753e6152a3ce13488eea22827cac9">tvm::relay::transform</a>
+</li>
<li>RemoveUnusedFunctions()
: <a class="el" href="namespacetvm_1_1relay_1_1transform.html#afbbf5f3e5ffb775fafb9c48473dbfa24">tvm::relay::transform</a>
</li>
@@ -148,7 +151,7 @@ $(function() {
</li>
<li>right_shift()
: <a class="el" href="namespacetvm.html#ae8ecc0382685a855187bede0c97d93e6">tvm</a>
-, <a class="el" href="namespacetvm_1_1topi.html#af4cded16f3e678f05304edf00566571e">tvm::topi</a>
+, <a class="el" href="namespacetvm_1_1topi.html#a9673b9caffb46404b566c3f04a492dfe">tvm::topi</a>
</li>
<li>rocblas_batch_matmul()
: <a class="el" href="namespacetvm_1_1topi_1_1contrib.html#abf1113dd429e1285752b48f62fe12848">tvm::topi::contrib</a>
diff --git a/docs/reference/api/doxygen/namespacemembers_s.html b/docs/reference/api/doxygen/namespacemembers_s.html
index e72b61c67..1f7d28aeb 100644
--- a/docs/reference/api/doxygen/namespacemembers_s.html
+++ b/docs/reference/api/doxygen/namespacemembers_s.html
@@ -279,12 +279,12 @@ $(function() {
<li>Specialize()
: <a class="el" href="namespacetvm_1_1tir.html#a69b6f1b0014dc6e7dd390cff746e9782">tvm::tir</a>
</li>
-<li>Split()
-: <a class="el" href="namespacetvm_1_1topi.html#a164125ca6dd5c4b677f72e63ce6b3c21">tvm::topi</a>
-</li>
<li>split()
: <a class="el" href="namespacetvm_1_1topi.html#af4e59b01a5842baf6b47ad3f83731f53">tvm::topi</a>
</li>
+<li>Split()
+: <a class="el" href="namespacetvm_1_1topi.html#a164125ca6dd5c4b677f72e63ce6b3c21">tvm::topi</a>
+</li>
<li>split_sections()
: <a class="el" href="namespacetvm_1_1topi.html#acc643e2ed166fa2ed82a95853e145619">tvm::topi</a>
</li>
@@ -359,7 +359,7 @@ $(function() {
: <a class="el" href="namespacetvm_1_1arith.html#aeb7d26b41b1cb5ea6aedba46715fcd7e">tvm::arith</a>
</li>
<li>Substitute()
-: <a class="el" href="namespacetvm_1_1tir.html#a34ae87f765e4d8230e3572428cdbe3e1">tvm::tir</a>
+: <a class="el" href="namespacetvm_1_1tir.html#aa5020900f638dead67cbeed15b478d6f">tvm::tir</a>
</li>
<li>SubstituteBoundVars()
: <a class="el" href="namespacetvm_1_1relay.html#aa65d5cde84db61b456ce982b5328fae2">tvm::relay</a>
diff --git a/docs/reference/api/doxygen/namespacemembers_u.html b/docs/reference/api/doxygen/namespacemembers_u.html
index dde0b0a24..e9a6194e2 100644
--- a/docs/reference/api/doxygen/namespacemembers_u.html
+++ b/docs/reference/api/doxygen/namespacemembers_u.html
@@ -64,8 +64,11 @@ $(function() {
<li>UnCPS()
: <a class="el" href="namespacetvm_1_1relay.html#a1677d450d58078811f52fd70d67db515">tvm::relay</a>
</li>
+<li>undef()
+: <a class="el" href="namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877">tvm::tir::builtin</a>
+</li>
<li>UndefinedVars()
-: <a class="el" href="namespacetvm_1_1tir.html#ae110e02855d8bc12eb8b6f92ed391844">tvm::tir</a>
+: <a class="el" href="namespacetvm_1_1tir.html#a99de316b20c7af2e8b4f06773ee69a5a">tvm::tir</a>
</li>
<li>UnifiedStaticMemoryPlanner()
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#aca44076eb1085d664877596a8b8587d4">tvm::tir::transform</a>
diff --git a/docs/reference/api/doxygen/namespacetvm_1_1relay_1_1transform.html b/docs/reference/api/doxygen/namespacetvm_1_1relay_1_1transform.html
index 618b3a4f6..405b10b67 100644
--- a/docs/reference/api/doxygen/namespacetvm_1_1relay_1_1transform.html
+++ b/docs/reference/api/doxygen/namespacetvm_1_1relay_1_1transform.html
@@ -226,6 +226,9 @@ Functions</h2></td></tr>
<tr class="memitem:a3d884f0646c7737a515c0430fb9674fa"><td class="memItemLeft" align="right" valign="top"><a class="el" href="namespacetvm_1_1relay_1_1transform.html#afa666ade112e9955059095d695238a9a">Pass</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1relay_1_1transform.html#a3d884f0646c7737a515c0430fb9674fa">AnnotateMemoryScope</a> (<a class="el" href="classtvm_1_1CompilationConfig.html">CompilationConfig</a> config)</td></tr>
<tr class="memdesc:a3d884f0646c7737a515c0430fb9674fa"><td class="mdescLeft"> </td><td class="mdescRight">Calls device dependent memory scope analysis pass, collects mapping of desirable expr->memory_scope and annotates expressions by <a class="el" href="classtvm_1_1VirtualDevice.html" title="Managed reference class to VirtualDeviceNode. ">VirtualDevice</a> with required memory_scope. <a href="#a3d884f0646c7737a515c0430fb9674fa">More...</a><br /></td></tr>
<tr class="separator:a3d884f0646c7737a515c0430fb9674fa"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:abf8753e6152a3ce13488eea22827cac9"><td class="memItemLeft" align="right" valign="top"><a class="el" href="namespacetvm_1_1relay_1_1transform.html#afa666ade112e9955059095d695238a9a">Pass</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1relay_1_1transform.html#abf8753e6152a3ce13488eea22827cac9">RemoveStandaloneReshapes</a> ()</td></tr>
+<tr class="memdesc:abf8753e6152a3ce13488eea22827cac9"><td class="mdescLeft"> </td><td class="mdescRight">Removes non-fused reshapes after lowering the graph. <a class="el" href="namespacetvm_1_1relay_1_1transform.html#a1a4fe2161bf32a60bc2e57debab083ee" title="Infer the type of an expression. ">InferType()</a> cannot be invoked after calling this pass as it removes reshapes from the call graph. Many targets only need buffer addresses irrespective of the shapes of them. This makes res [...]
+<tr class="separator:abf8753e6152a3ce13488eea22827cac9"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<h2 class="groupheader">Typedef Documentation</h2>
<a id="afa666ade112e9955059095d695238a9a"></a>
@@ -1222,6 +1225,25 @@ Functions</h2></td></tr>
</dl>
<dl class="section return"><dt>Returns</dt><dd>The pass. </dd></dl>
+</div>
+</div>
+<a id="abf8753e6152a3ce13488eea22827cac9"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#abf8753e6152a3ce13488eea22827cac9">◆ </a></span>RemoveStandaloneReshapes()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname"><a class="el" href="namespacetvm_1_1relay_1_1transform.html#afa666ade112e9955059095d695238a9a">Pass</a> tvm::relay::transform::RemoveStandaloneReshapes </td>
+ <td>(</td>
+ <td class="paramname"></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Removes non-fused reshapes after lowering the graph. <a class="el" href="namespacetvm_1_1relay_1_1transform.html#a1a4fe2161bf32a60bc2e57debab083ee" title="Infer the type of an expression. ">InferType()</a> cannot be invoked after calling this pass as it removes reshapes from the call graph. Many targets only need buffer addresses irrespective of the shapes of them. This makes reshapes symbolic once the graph has been lowered. Reshape removal results into smaller code size and reduced [...]
+
</div>
</div>
<a id="afbbf5f3e5ffb775fafb9c48473dbfa24"></a>
diff --git a/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1builtin.html b/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1builtin.html
index 75e1bcf94..de5a6ea44 100644
--- a/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1builtin.html
+++ b/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1builtin.html
@@ -309,6 +309,9 @@ Functions</h2></td></tr>
<tr class="memitem:a0b3d8f41abba4b7dd4a9af8ec2f9acba"><td class="memItemLeft" align="right" valign="top">const <a class="el" href="classtvm_1_1Op.html">Op</a> & </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1builtin.html#a0b3d8f41abba4b7dd4a9af8ec2f9acba">assume</a> ()</td></tr>
<tr class="memdesc:a0b3d8f41abba4b7dd4a9af8ec2f9acba"><td class="mdescLeft"> </td><td class="mdescRight">Provide a true statement that can be used for simplifications. <a href="#a0b3d8f41abba4b7dd4a9af8ec2f9acba">More...</a><br /></td></tr>
<tr class="separator:a0b3d8f41abba4b7dd4a9af8ec2f9acba"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a77a72a2e21fe0ea2118479924b4fb877"><td class="memItemLeft" align="right" valign="top">const <a class="el" href="classtvm_1_1Op.html">Op</a> & </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877">undef</a> ()</td></tr>
+<tr class="memdesc:a77a72a2e21fe0ea2118479924b4fb877"><td class="mdescLeft"> </td><td class="mdescRight">Returns an initialized but arbitrary value. <a href="#a77a72a2e21fe0ea2118479924b4fb877">More...</a><br /></td></tr>
+<tr class="separator:a77a72a2e21fe0ea2118479924b4fb877"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
<div class="textblock"><p>Collection of builtin intrinsics as ops. </p>
@@ -1690,6 +1693,26 @@ Functions</h2></td></tr>
</table>
</div><div class="memdoc">
+</div>
+</div>
+<a id="a77a72a2e21fe0ea2118479924b4fb877"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a77a72a2e21fe0ea2118479924b4fb877">◆ </a></span>undef()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">const <a class="el" href="classtvm_1_1Op.html">Op</a>& tvm::tir::builtin::undef </td>
+ <td>(</td>
+ <td class="paramname"></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Returns an initialized but arbitrary value. </p>
+<p>Compile-time representation of memory locations whose values may be altered as a result of optimizations. </p>
+
</div>
</div>
<a id="a30dff65bc2c142b57fae7f60e378ff43"></a>
diff --git a/docs/reference/api/doxygen/relay_2transform_8h.html b/docs/reference/api/doxygen/relay_2transform_8h.html
index 74749c8af..f7e3c48f9 100644
--- a/docs/reference/api/doxygen/relay_2transform_8h.html
+++ b/docs/reference/api/doxygen/relay_2transform_8h.html
@@ -265,6 +265,9 @@ Functions</h2></td></tr>
<tr class="memitem:a3d884f0646c7737a515c0430fb9674fa"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1relay_1_1transform.html#a3d884f0646c7737a515c0430fb9674fa">tvm::relay::transform::AnnotateMemoryScope</a> (CompilationConfig config)</td></tr>
<tr class="memdesc:a3d884f0646c7737a515c0430fb9674fa"><td class="mdescLeft"> </td><td class="mdescRight">Calls device dependent memory scope analysis pass, collects mapping of desirable expr->memory_scope and annotates expressions by <a class="el" href="classtvm_1_1VirtualDevice.html" title="Managed reference class to VirtualDeviceNode. ">VirtualDevice</a> with required memory_scope. <a href="namespacetvm_1_1relay_1_1transform.html#a3d884f0646c7737a515c0430fb9674fa">More...</a>< [...]
<tr class="separator:a3d884f0646c7737a515c0430fb9674fa"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:abf8753e6152a3ce13488eea22827cac9"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1relay_1_1transform.html#abf8753e6152a3ce13488eea22827cac9">tvm::relay::transform::RemoveStandaloneReshapes</a> ()</td></tr>
+<tr class="memdesc:abf8753e6152a3ce13488eea22827cac9"><td class="mdescLeft"> </td><td class="mdescRight">Removes non-fused reshapes after lowering the graph. <a class="el" href="namespacetvm_1_1relay_1_1transform.html#a1a4fe2161bf32a60bc2e57debab083ee" title="Infer the type of an expression. ">InferType()</a> cannot be invoked after calling this pass as it removes reshapes from the call graph. Many targets only need buffer addresses irrespective of the shapes of them. This makes res [...]
+<tr class="separator:abf8753e6152a3ce13488eea22827cac9"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:ad7cfa0b6a4537989b886d47767526726"><td class="memItemLeft" align="right" valign="top">Expr </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1relay.html#ad7cfa0b6a4537989b886d47767526726">tvm::relay::Bind</a> (const Expr &expr, const <a class="el" href="classtvm_1_1runtime_1_1Map.html">tvm::Map</a>< Var, Expr > &binds)</td></tr>
<tr class="memdesc:ad7cfa0b6a4537989b886d47767526726"><td class="mdescLeft"> </td><td class="mdescRight">Bind the free variables to a Relay expression. This is a helper function usually called by other pass functions to help optimizations. <a class="el" href="classtvm_1_1relay_1_1If.html">If</a> any free variables are introduced into a function, those are added to the functoin parameters. Additionally this may change the order of parameters if you map a variable to a variable. <a h [...]
<tr class="separator:ad7cfa0b6a4537989b886d47767526726"><td class="memSeparator" colspan="2"> </td></tr>
diff --git a/docs/reference/api/doxygen/relay_2transform_8h_source.html b/docs/reference/api/doxygen/relay_2transform_8h_source.html
index a61e59721..7f69ee7dc 100644
--- a/docs/reference/api/doxygen/relay_2transform_8h_source.html
+++ b/docs/reference/api/doxygen/relay_2transform_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">transform.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="relay_2transform_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
+<a href="relay_2transform_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
<div class="ttc" id="classtvm_1_1CompilationConfig_html"><div class="ttname"><a href="classtvm_1_1CompilationConfig.html">tvm::CompilationConfig</a></div><div class="ttdoc">Managed reference class to CompilationConfig. </div><div class="ttdef"><b>Definition:</b> compilation_config.h:191</div></div>
<div class="ttc" id="namespacetvm_1_1relay_1_1transform_html_ad90e4d6ac08b62ef553755e759d398fa"><div class="ttname"><a href="namespacetvm_1_1relay_1_1transform.html#ad90e4d6ac08b62ef553755e759d398fa">tvm::relay::transform::ToCPS</a></div><div class="ttdeci">Pass ToCPS()</div><div class="ttdoc">Turn an expression into continuation passing style(CPS). </div></div>
<div class="ttc" id="namespacetvm_1_1relay_1_1transform_html_a93bbf7ab3f612d4f38a6832d6b53b4fd"><div class="ttname"><a href="namespacetvm_1_1relay_1_1transform.html#a93bbf7ab3f612d4f38a6832d6b53b4fd">tvm::relay::transform::CanonicalizeCast</a></div><div class="ttdeci">Pass CanonicalizeCast()</div><div class="ttdoc">Canonicalize cast expressions to make operator fusion more efficient. </div></div>
@@ -140,6 +140,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1Map_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Map.html">tvm::runtime::Map</a></div><div class="ttdoc">Map container of NodeRef->NodeRef in DSL graph. Map implements copy on write semantics, which means map is mutable but copy will happen when array is referenced in more than two places. </div><div class="ttdef"><b>Definition:</b> map.h:1268</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1PackedFunc_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1PackedFunc.html">tvm::runtime::PackedFunc</a></div><div class="ttdoc">Packed function is a type-erased function. The arguments are passed by packed format. </div><div class="ttdef"><b>Definition:</b> packed_func.h:138</div></div>
<div class="ttc" id="classtvm_1_1Type_html"><div class="ttname"><a href="classtvm_1_1Type.html">tvm::Type</a></div><div class="ttdoc">Managed reference to TypeNode. </div><div class="ttdef"><b>Definition:</b> type.h:93</div></div>
+<div class="ttc" id="namespacetvm_1_1relay_1_1transform_html_abf8753e6152a3ce13488eea22827cac9"><div class="ttname"><a href="namespacetvm_1_1relay_1_1transform.html#abf8753e6152a3ce13488eea22827cac9">tvm::relay::transform::RemoveStandaloneReshapes</a></div><div class="ttdeci">Pass RemoveStandaloneReshapes()</div><div class="ttdoc">Removes non-fused reshapes after lowering the graph. InferType() cannot be invoked after calling this...</div></div>
<div class="ttc" id="namespacetvm_1_1relay_1_1transform_html_aa97a0ec61929f58aefff5da83a73e1cd"><div class="ttname"><a href="namespacetvm_1_1relay_1_1transform.html#aa97a0ec61929f58aefff5da83a73e1cd">tvm::relay::transform::CombineParallelBatchMatmul</a></div><div class="ttdeci">Pass CombineParallelBatchMatmul(uint64_t min_num_branches=3)</div><div class="ttdoc">Combine parallel batch_matmul ops into a single batch_matmul if the number of branches of this dense ...</div></div>
<div class="ttc" id="namespacetvm_1_1relay_1_1transform_html_af719f05ee653ea465589a38747b35e22"><div class="ttname"><a href="namespacetvm_1_1relay_1_1transform.html#af719f05ee653ea465589a38747b35e22">tvm::relay::transform::FlattenAtrousConv</a></div><div class="ttdeci">Pass FlattenAtrousConv()</div><div class="ttdoc">This transform flattens atrous convolution, which corresponds to the sequence of operations: "space_t...</div></div>
<div class="ttc" id="namespacetvm_1_1relay_1_1transform_html_a0d850ee9bfb41de42cf3a2bb25586528"><div class="ttname"><a href="namespacetvm_1_1relay_1_1transform.html#a0d850ee9bfb41de42cf3a2bb25586528">tvm::relay::transform::CapturePostDfsIndexInSpans</a></div><div class="ttdeci">Pass CapturePostDfsIndexInSpans()</div><div class="ttdoc">Captures the post-dfs index and dominator post-dfs index of (most) expression nodes in their span...</div></div>
diff --git a/docs/reference/api/doxygen/search/all_11.js b/docs/reference/api/doxygen/search/all_11.js
index 8288ae024..69bde4c4a 100644
--- a/docs/reference/api/doxygen/search/all_11.js
+++ b/docs/reference/api/doxygen/search/all_11.js
@@ -21,7 +21,7 @@ var searchData=
['packetfieldsizebytes',['PacketFieldSizeBytes',['../classtvm_1_1runtime_1_1micro__rpc_1_1PacketFieldSizeBytes.html',1,'tvm::runtime::micro_rpc']]],
['packimportstoc',['PackImportsToC',['../namespacetvm_1_1codegen.html#abf02059ebadcdb8bbbe5c840b646d67b',1,'tvm::codegen']]],
['packimportstollvm',['PackImportsToLLVM',['../namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6',1,'tvm::codegen']]],
- ['pad',['Pad',['../namespacetvm_1_1topi.html#a97c798d0a0ec20a95d351618b83d5121',1,'tvm::topi::Pad(const Array< PrimExpr > shape, int odim)'],['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElement [...]
+ ['pad',['pad',['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElementWise, std::string pad_mode="constant", const Array< PrimExpr > *dyn_output_shape=nullptr)'],['../namespacetvm_1_1topi [...]
['pad_5fmode',['pad_mode',['../structtvm_1_1relay_1_1PadAttrs.html#a5b524c3add781cd2da894e81553079f8',1,'tvm::relay::PadAttrs']]],
['pad_5futils_2eh',['pad_utils.h',['../pad__utils_8h.html',1,'']]],
['pad_5fvalue',['pad_value',['../structtvm_1_1relay_1_1SpaceToBatchNDAttrs.html#a7c0fbd47621c925a45e1074f85a6b70f',1,'tvm::relay::SpaceToBatchNDAttrs']]],
diff --git a/docs/reference/api/doxygen/search/all_13.js b/docs/reference/api/doxygen/search/all_13.js
index 749371e2f..56bb647bb 100644
--- a/docs/reference/api/doxygen/search/all_13.js
+++ b/docs/reference/api/doxygen/search/all_13.js
@@ -108,6 +108,7 @@ var searchData=
['removenoop',['RemoveNoOp',['../namespacetvm_1_1tir_1_1transform.html#a8aad1159425e29be796562b2ec629b10',1,'tvm::tir::transform']]],
['removerpcsessionmask',['RemoveRPCSessionMask',['../namespacetvm_1_1runtime.html#af32398517b6b915361c5716f8e32c16f',1,'tvm::runtime']]],
['removerv',['RemoveRV',['../classtvm_1_1tir_1_1ScheduleNode.html#a70d353bb52f6fa29fedeb90a6ff872d5',1,'tvm::tir::ScheduleNode::RemoveRV(const BlockRV &block_rv)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#a7c44d4f4ea662291ccb9d79383b6fefe',1,'tvm::tir::ScheduleNode::RemoveRV(const LoopRV &loop_rv)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#a00fcf343d2bc8f36f170c04e5e29d2dc',1,'tvm::tir::ScheduleNode::RemoveRV(const ExprRV &expr_rv)=0']]],
+ ['removestandalonereshapes',['RemoveStandaloneReshapes',['../namespacetvm_1_1relay_1_1transform.html#abf8753e6152a3ce13488eea22827cac9',1,'tvm::relay::transform']]],
['removeunusedfunctions',['RemoveUnusedFunctions',['../namespacetvm_1_1relay_1_1transform.html#afbbf5f3e5ffb775fafb9c48473dbfa24',1,'tvm::relay::transform']]],
['removeweightlayoutrewriteblock',['RemoveWeightLayoutRewriteBlock',['../namespacetvm_1_1tir_1_1transform.html#a3751bb39f2b5fe3b9ef20fd57db828e5',1,'tvm::tir::transform']]],
['rend',['rend',['../classtvm_1_1runtime_1_1Array.html#a1dda4b706346d1299cea059957e9ee70',1,'tvm::runtime::Array']]],
diff --git a/docs/reference/api/doxygen/search/all_14.js b/docs/reference/api/doxygen/search/all_14.js
index 0a691047d..e69c3d6d9 100644
--- a/docs/reference/api/doxygen/search/all_14.js
+++ b/docs/reference/api/doxygen/search/all_14.js
@@ -168,7 +168,7 @@ var searchData=
['setvalue_3c_20uint64_5ft_20_3e',['SetValue< uint64_t >',['../namespacetvm_1_1detail.html#acb3382242cbf538f64edae13e4ec5a84',1,'tvm::detail']]],
['shallowcopy',['ShallowCopy',['../classtvm_1_1IRModuleNode.html#a86bbdc4b857ce5958a2b5f29e1d6fcb6',1,'tvm::IRModuleNode']]],
['shallowcopyirmodule',['ShallowCopyIRModule',['../classtvm_1_1IRModule.html#aea8b821cf92cf525bd87bf15f5d31889',1,'tvm::IRModule']]],
- ['shape',['shape',['../classtvm_1_1TensorTypeNode.html#a98fa347833e4504dd6f8056d9863a708',1,'tvm::TensorTypeNode::shape()'],['../classtvm_1_1meta__schedule_1_1TensorInfoNode.html#ac16d3b10f7c68eefb27e55e865bb304c',1,'tvm::meta_schedule::TensorInfoNode::shape()'],['../structtvm_1_1relay_1_1InitOpAttrs.html#aaaec76cc5ea9a543c4ea174a6b38bf5e',1,'tvm::relay::InitOpAttrs::shape()'],['../classtvm_1_1relay_1_1ShapePatternNode.html#a749813cbbd38f8021a7df897d527d6e0',1,'tvm::relay::ShapePattern [...]
+ ['shape',['shape',['../classtvm_1_1TensorTypeNode.html#a98fa347833e4504dd6f8056d9863a708',1,'tvm::TensorTypeNode::shape()'],['../classtvm_1_1meta__schedule_1_1TensorInfoNode.html#ac16d3b10f7c68eefb27e55e865bb304c',1,'tvm::meta_schedule::TensorInfoNode::shape()'],['../structtvm_1_1relay_1_1InitOpAttrs.html#aaaec76cc5ea9a543c4ea174a6b38bf5e',1,'tvm::relay::InitOpAttrs::shape()'],['../classtvm_1_1relay_1_1ShapePatternNode.html#a749813cbbd38f8021a7df897d527d6e0',1,'tvm::relay::ShapePattern [...]
['shape_5f',['shape_',['../classtvm_1_1runtime_1_1NDArray_1_1ContainerBase.html#aa5597a1760c9f8c9d1fd51584b1283fb',1,'tvm::runtime::NDArray::ContainerBase']]],
['shape_5fbackward_5frule',['shape_backward_rule',['../classtvm_1_1tir_1_1BijectiveLayoutNode.html#a0befdd0a2371c0d12970e8ac6623b59b',1,'tvm::tir::BijectiveLayoutNode']]],
['shape_5fcount',['shape_count',['../structTVMGraphExecutorGraphAttr.html#a182b228582f1186f2a15de50a25b3375',1,'TVMGraphExecutorGraphAttr']]],
@@ -277,7 +277,7 @@ var searchData=
['specialize',['Specialize',['../namespacetvm_1_1tir.html#a69b6f1b0014dc6e7dd390cff746e9782',1,'tvm::tir']]],
['specializedcondition',['SpecializedCondition',['../classtvm_1_1te_1_1SpecializedCondition.html',1,'tvm::te::SpecializedCondition'],['../classtvm_1_1te_1_1SpecializedCondition.html#a48d119ee1c6033929a5592cfc2592e60',1,'tvm::te::SpecializedCondition::SpecializedCondition()']]],
['specializedconditionnode',['SpecializedConditionNode',['../classtvm_1_1te_1_1SpecializedConditionNode.html',1,'tvm::te']]],
- ['split',['Split',['../classtvm_1_1te_1_1Split.html',1,'tvm::te::Split'],['../classtvm_1_1te_1_1Split.html#a328e0c093ce5b41ebaf33e0e80592764',1,'tvm::te::Split::Split()'],['../classtvm_1_1tir_1_1Layout.html#ad7657af7789fe040d3224c0149976bb4',1,'tvm::tir::Layout::Split()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ac190a0ab76d8754a35209479bcc6dfa2',1,'tvm::tir::ScheduleNode::Split()'],['../classtvm_1_1auto__scheduler_1_1State.html#a5815f21fc90ba7cc379c2410c05ab54c',1,'tvm::auto_schedule [...]
+ ['split',['Split',['../classtvm_1_1te_1_1Split.html',1,'tvm::te::Split'],['../classtvm_1_1te_1_1Split.html#a328e0c093ce5b41ebaf33e0e80592764',1,'tvm::te::Split::Split()'],['../classtvm_1_1tir_1_1Layout.html#ad7657af7789fe040d3224c0149976bb4',1,'tvm::tir::Layout::Split()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ac190a0ab76d8754a35209479bcc6dfa2',1,'tvm::tir::ScheduleNode::Split()'],['../classtvm_1_1auto__scheduler_1_1State.html#a5815f21fc90ba7cc379c2410c05ab54c',1,'tvm::auto_schedule [...]
['split_5fby_5fnparts',['split_by_nparts',['../classtvm_1_1te_1_1Stage.html#a51432f38d9ec4792a2525023179ae604',1,'tvm::te::Stage']]],
['split_5fsections',['split_sections',['../namespacetvm_1_1topi.html#acc643e2ed166fa2ed82a95853e145619',1,'tvm::topi']]],
['splitargs',['SplitArgs',['../namespacetvm_1_1relay_1_1transform.html#a2425d757b896168a109498e8d34ba960',1,'tvm::relay::transform']]],
diff --git a/docs/reference/api/doxygen/search/all_16.js b/docs/reference/api/doxygen/search/all_16.js
index ac10518d9..e37351add 100644
--- a/docs/reference/api/doxygen/search/all_16.js
+++ b/docs/reference/api/doxygen/search/all_16.js
@@ -4,7 +4,7 @@ var searchData=
['unannotate',['Unannotate',['../classtvm_1_1tir_1_1ScheduleNode.html#a45cd553c09ec836dfcbff81379647f07',1,'tvm::tir::ScheduleNode::Unannotate(const LoopRV &loop_rv, const String &ann_key)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#a7c310bca5d1583e61a3f27052a1dd5d0',1,'tvm::tir::ScheduleNode::Unannotate(const BlockRV &block_rv, const String &ann_key)=0']]],
['unbiased',['unbiased',['../structtvm_1_1relay_1_1VarianceAttrs.html#a7de5da9ca0327074013e5c1ed7e9a5ed',1,'tvm::relay::VarianceAttrs']]],
['uncps',['UnCPS',['../namespacetvm_1_1relay.html#a1677d450d58078811f52fd70d67db515',1,'tvm::relay']]],
- ['undef',['Undef',['../classtvm_1_1tir_1_1Layout.html#a1c7bdf466d341ad61aba104db318ee0e',1,'tvm::tir::Layout']]],
+ ['undef',['Undef',['../classtvm_1_1tir_1_1Layout.html#a1c7bdf466d341ad61aba104db318ee0e',1,'tvm::tir::Layout::Undef()'],['../namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877',1,'tvm::tir::builtin::undef()']]],
['undefinedvars',['UndefinedVars',['../namespacetvm_1_1tir.html#ae110e02855d8bc12eb8b6f92ed391844',1,'tvm::tir::UndefinedVars(const Stmt &stmt, const Array< Var > &defs)'],['../namespacetvm_1_1tir.html#a99de316b20c7af2e8b4f06773ee69a5a',1,'tvm::tir::UndefinedVars(const PrimExpr &expr)']]],
['unframer',['Unframer',['../classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html',1,'tvm::runtime::micro_rpc::Unframer'],['../classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html#a58d68e70d1819a706669c9934dd07639',1,'tvm::runtime::micro_rpc::Unframer::Unframer()']]],
['unifiedstaticmemoryplanner',['UnifiedStaticMemoryPlanner',['../namespacetvm_1_1tir_1_1transform.html#aca44076eb1085d664877596a8b8587d4',1,'tvm::tir::transform']]],
diff --git a/docs/reference/api/doxygen/search/functions_10.js b/docs/reference/api/doxygen/search/functions_10.js
index b5cc125d3..96cb67eab 100644
--- a/docs/reference/api/doxygen/search/functions_10.js
+++ b/docs/reference/api/doxygen/search/functions_10.js
@@ -7,7 +7,7 @@ var searchData=
['packetdone',['PacketDone',['../classtvm_1_1runtime_1_1micro__rpc_1_1WriteStream.html#a1745b7d9d5a0e094e129eb7a4c363ac9',1,'tvm::runtime::micro_rpc::WriteStream']]],
['packimportstoc',['PackImportsToC',['../namespacetvm_1_1codegen.html#abf02059ebadcdb8bbbe5c840b646d67b',1,'tvm::codegen']]],
['packimportstollvm',['PackImportsToLLVM',['../namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6',1,'tvm::codegen']]],
- ['pad',['Pad',['../namespacetvm_1_1topi.html#a97c798d0a0ec20a95d351618b83d5121',1,'tvm::topi::Pad(const Array< PrimExpr > shape, int odim)'],['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElement [...]
+ ['pad',['pad',['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElementWise, std::string pad_mode="constant", const Array< PrimExpr > *dyn_output_shape=nullptr)'],['../namespacetvm_1_1topi [...]
['pagememorymanagercreate',['PageMemoryManagerCreate',['../page__allocator_8h.html#a720dbc7474ac13b93fafb974cfc20bc7',1,'page_allocator.h']]],
['parallel',['parallel',['../classtvm_1_1auto__scheduler_1_1State.html#a2376f0180bc5b5dd4b456f2a75d4a366',1,'tvm::auto_scheduler::State::parallel()'],['../classtvm_1_1te_1_1Stage.html#a60a6be10a1a96cb594c1399efabafef3',1,'tvm::te::Stage::parallel()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a553dc17c0b49b175cd16881c81b6c789',1,'tvm::tir::ScheduleNode::Parallel()']]],
['parallel_5ffor',['parallel_for',['../namespacetvm_1_1support.html#a8bf1225e8bb1db575578ca2d645fb23c',1,'tvm::support']]],
diff --git a/docs/reference/api/doxygen/search/functions_12.js b/docs/reference/api/doxygen/search/functions_12.js
index 923180fa0..d6984131c 100644
--- a/docs/reference/api/doxygen/search/functions_12.js
+++ b/docs/reference/api/doxygen/search/functions_12.js
@@ -46,6 +46,7 @@ var searchData=
['removenoop',['RemoveNoOp',['../namespacetvm_1_1tir_1_1transform.html#a8aad1159425e29be796562b2ec629b10',1,'tvm::tir::transform']]],
['removerpcsessionmask',['RemoveRPCSessionMask',['../namespacetvm_1_1runtime.html#af32398517b6b915361c5716f8e32c16f',1,'tvm::runtime']]],
['removerv',['RemoveRV',['../classtvm_1_1tir_1_1ScheduleNode.html#a70d353bb52f6fa29fedeb90a6ff872d5',1,'tvm::tir::ScheduleNode::RemoveRV(const BlockRV &block_rv)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#a7c44d4f4ea662291ccb9d79383b6fefe',1,'tvm::tir::ScheduleNode::RemoveRV(const LoopRV &loop_rv)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#a00fcf343d2bc8f36f170c04e5e29d2dc',1,'tvm::tir::ScheduleNode::RemoveRV(const ExprRV &expr_rv)=0']]],
+ ['removestandalonereshapes',['RemoveStandaloneReshapes',['../namespacetvm_1_1relay_1_1transform.html#abf8753e6152a3ce13488eea22827cac9',1,'tvm::relay::transform']]],
['removeunusedfunctions',['RemoveUnusedFunctions',['../namespacetvm_1_1relay_1_1transform.html#afbbf5f3e5ffb775fafb9c48473dbfa24',1,'tvm::relay::transform']]],
['removeweightlayoutrewriteblock',['RemoveWeightLayoutRewriteBlock',['../namespacetvm_1_1tir_1_1transform.html#a3751bb39f2b5fe3b9ef20fd57db828e5',1,'tvm::tir::transform']]],
['rend',['rend',['../classtvm_1_1runtime_1_1Array.html#a1dda4b706346d1299cea059957e9ee70',1,'tvm::runtime::Array']]],
diff --git a/docs/reference/api/doxygen/search/functions_13.js b/docs/reference/api/doxygen/search/functions_13.js
index 823360633..9ccd513cd 100644
--- a/docs/reference/api/doxygen/search/functions_13.js
+++ b/docs/reference/api/doxygen/search/functions_13.js
@@ -149,7 +149,7 @@ var searchData=
['sparse_5fto_5fdense',['sparse_to_dense',['../namespacetvm_1_1topi.html#a877e6fdffb6b6c051c29602ec6fe995c',1,'tvm::topi']]],
['specialize',['Specialize',['../namespacetvm_1_1tir.html#a69b6f1b0014dc6e7dd390cff746e9782',1,'tvm::tir']]],
['specializedcondition',['SpecializedCondition',['../classtvm_1_1te_1_1SpecializedCondition.html#a48d119ee1c6033929a5592cfc2592e60',1,'tvm::te::SpecializedCondition']]],
- ['split',['Split',['../classtvm_1_1te_1_1Split.html#a328e0c093ce5b41ebaf33e0e80592764',1,'tvm::te::Split::Split()'],['../classtvm_1_1tir_1_1Layout.html#ad7657af7789fe040d3224c0149976bb4',1,'tvm::tir::Layout::Split()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ac190a0ab76d8754a35209479bcc6dfa2',1,'tvm::tir::ScheduleNode::Split()'],['../classtvm_1_1auto__scheduler_1_1State.html#a5815f21fc90ba7cc379c2410c05ab54c',1,'tvm::auto_scheduler::State::split()'],['../classtvm_1_1te_1_1Stage.html#a [...]
+ ['split',['Split',['../classtvm_1_1te_1_1Split.html#a328e0c093ce5b41ebaf33e0e80592764',1,'tvm::te::Split::Split()'],['../classtvm_1_1tir_1_1Layout.html#ad7657af7789fe040d3224c0149976bb4',1,'tvm::tir::Layout::Split()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ac190a0ab76d8754a35209479bcc6dfa2',1,'tvm::tir::ScheduleNode::Split()'],['../classtvm_1_1auto__scheduler_1_1State.html#a5815f21fc90ba7cc379c2410c05ab54c',1,'tvm::auto_scheduler::State::split()'],['../classtvm_1_1te_1_1Stage.html#a [...]
['split_5fby_5fnparts',['split_by_nparts',['../classtvm_1_1te_1_1Stage.html#a51432f38d9ec4792a2525023179ae604',1,'tvm::te::Stage']]],
['split_5fsections',['split_sections',['../namespacetvm_1_1topi.html#acc643e2ed166fa2ed82a95853e145619',1,'tvm::topi']]],
['splitargs',['SplitArgs',['../namespacetvm_1_1relay_1_1transform.html#a2425d757b896168a109498e8d34ba960',1,'tvm::relay::transform']]],
diff --git a/docs/reference/api/doxygen/search/functions_15.js b/docs/reference/api/doxygen/search/functions_15.js
index e36cafb01..b778a64f9 100644
--- a/docs/reference/api/doxygen/search/functions_15.js
+++ b/docs/reference/api/doxygen/search/functions_15.js
@@ -3,7 +3,7 @@ var searchData=
['uint',['UInt',['../classtvm_1_1runtime_1_1DataType.html#ad1cf4571ee1a22c188c66ee2e6e6c042',1,'tvm::runtime::DataType']]],
['unannotate',['Unannotate',['../classtvm_1_1tir_1_1ScheduleNode.html#a45cd553c09ec836dfcbff81379647f07',1,'tvm::tir::ScheduleNode::Unannotate(const LoopRV &loop_rv, const String &ann_key)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#a7c310bca5d1583e61a3f27052a1dd5d0',1,'tvm::tir::ScheduleNode::Unannotate(const BlockRV &block_rv, const String &ann_key)=0']]],
['uncps',['UnCPS',['../namespacetvm_1_1relay.html#a1677d450d58078811f52fd70d67db515',1,'tvm::relay']]],
- ['undef',['Undef',['../classtvm_1_1tir_1_1Layout.html#a1c7bdf466d341ad61aba104db318ee0e',1,'tvm::tir::Layout']]],
+ ['undef',['Undef',['../classtvm_1_1tir_1_1Layout.html#a1c7bdf466d341ad61aba104db318ee0e',1,'tvm::tir::Layout::Undef()'],['../namespacetvm_1_1tir_1_1builtin.html#a77a72a2e21fe0ea2118479924b4fb877',1,'tvm::tir::builtin::undef()']]],
['undefinedvars',['UndefinedVars',['../namespacetvm_1_1tir.html#ae110e02855d8bc12eb8b6f92ed391844',1,'tvm::tir::UndefinedVars(const Stmt &stmt, const Array< Var > &defs)'],['../namespacetvm_1_1tir.html#a99de316b20c7af2e8b4f06773ee69a5a',1,'tvm::tir::UndefinedVars(const PrimExpr &expr)']]],
['unframer',['Unframer',['../classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html#a58d68e70d1819a706669c9934dd07639',1,'tvm::runtime::micro_rpc::Unframer']]],
['unifiedstaticmemoryplanner',['UnifiedStaticMemoryPlanner',['../namespacetvm_1_1tir_1_1transform.html#aca44076eb1085d664877596a8b8587d4',1,'tvm::tir::transform']]],
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 7ed534894..0fb5c3826 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index 14ad0789d..6fdeb768f 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -6233,14 +6233,14 @@ block are divisible by the subspace represented by the loops starting at the giv
<dl class="py method">
<dt class="sig sig-object py" id="tvm.tir.Schedule.annotate">
-<span class="sig-name descname"><span class="pre">annotate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">block_or_loop</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">tvm.tir.schedule.schedule.BlockRV</span><span class="p"><span class="pre">,</span> </span><span class="pre">tvm.tir.schedule.schedule.LoopRV</ [...]
+<span class="sig-name descname"><span class="pre">annotate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">block_or_loop</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">tvm.tir.schedule.schedule.BlockRV</span><span class="p"><span class="pre">,</span> </span><span class="pre">tvm.tir.schedule.schedule.LoopRV</ [...]
<dd><p>Annotate a block/loop with a key value pair</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>block_or_loop</strong> (<em>Union</em><em>[</em><em>BlockRV</em><em>, </em><em>LoopRV</em><em>]</em>) – The block/loop to be annotated</p></li>
<li><p><strong>ann_key</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a>) – The annotation key</p></li>
-<li><p><strong>ann_val</strong> (<em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.10)"><em>float</em></a><em>, </em><em [...]
+<li><p><strong>ann_val</strong> (<em>AnnotationValueT</em>) – The annotation value</p></li>
</ul>
</dd>
</dl>
@@ -6749,46 +6749,49 @@ reads/writes of the block.</p>
<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.RemoveNoOp" title="tvm.tir.transform.RemoveNoOp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RemoveNoOp</span></code></a>()</p></td>
<td><p>Remove No Op from the Stmt.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.RemoveWeightLayoutRewriteBlock" title="tvm.tir.transform.RemoveWeightLayoutRewriteBlock"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RemoveWeightLayoutRewriteBlock</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.RemoveStoreUndef" title="tvm.tir.transform.RemoveStoreUndef"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RemoveStoreUndef</span></code></a>()</p></td>
+<td><p>Remove stores of undefined values from the Stmt.</p></td>
+</tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.RemoveWeightLayoutRewriteBlock" title="tvm.tir.transform.RemoveWeightLayoutRewriteBlock"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RemoveWeightLayoutRewriteBlock</span></code></a>()</p></td>
<td><p>Remove weight layout rewrite block before benchmarking during tuning stage.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.RenormalizeSplitPattern" title="tvm.tir.transform.RenormalizeSplitPattern"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RenormalizeSplitPattern</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.RenormalizeSplitPattern" title="tvm.tir.transform.RenormalizeSplitPattern"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RenormalizeSplitPattern</span></code></a>()</p></td>
<td><p>Renormalize the split pattern from floordiv(floormod()) to floormod(floordiv())</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.RewriteUnsafeSelect" title="tvm.tir.transform.RewriteUnsafeSelect"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RewriteUnsafeSelect</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.RewriteUnsafeSelect" title="tvm.tir.transform.RewriteUnsafeSelect"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RewriteUnsafeSelect</span></code></a>()</p></td>
<td><p>Detect and rewrite unsafe select that contains memory access.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.Simplify" title="tvm.tir.transform.Simplify"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Simplify</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.Simplify" title="tvm.tir.transform.Simplify"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Simplify</span></code></a>()</p></td>
<td><p>Run arithmetic simplifications on the statements and expressions.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.SkipAssert" title="tvm.tir.transform.SkipAssert"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SkipAssert</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.SkipAssert" title="tvm.tir.transform.SkipAssert"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SkipAssert</span></code></a>()</p></td>
<td><p>Skip assert stmt.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.SplitHostDevice" title="tvm.tir.transform.SplitHostDevice"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SplitHostDevice</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.SplitHostDevice" title="tvm.tir.transform.SplitHostDevice"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SplitHostDevice</span></code></a>()</p></td>
<td><p>Split the function into a host function and device functions.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.StorageFlatten" title="tvm.tir.transform.StorageFlatten"><code class="xref py py-obj docutils literal notranslate"><span class="pre">StorageFlatten</span></code></a>(cache_line_size[, ...])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.StorageFlatten" title="tvm.tir.transform.StorageFlatten"><code class="xref py py-obj docutils literal notranslate"><span class="pre">StorageFlatten</span></code></a>(cache_line_size[, ...])</p></td>
<td><p>Flatten the multi-dimensional read/write to 1D.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.StorageRewrite" title="tvm.tir.transform.StorageRewrite"><code class="xref py py-obj docutils literal notranslate"><span class="pre">StorageRewrite</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.StorageRewrite" title="tvm.tir.transform.StorageRewrite"><code class="xref py py-obj docutils literal notranslate"><span class="pre">StorageRewrite</span></code></a>()</p></td>
<td><p>Rewrite storage allocation pattern.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.TextureFlatten" title="tvm.tir.transform.TextureFlatten"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TextureFlatten</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.TextureFlatten" title="tvm.tir.transform.TextureFlatten"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TextureFlatten</span></code></a>()</p></td>
<td><p>Flatten the multi-dimensional read/write to 2D.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.ThreadSync" title="tvm.tir.transform.ThreadSync"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ThreadSync</span></code></a>(storage_scope)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.ThreadSync" title="tvm.tir.transform.ThreadSync"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ThreadSync</span></code></a>(storage_scope)</p></td>
<td><p>Insert sync between parallel read/write of shared buffers.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.UnifyThreadBinding" title="tvm.tir.transform.UnifyThreadBinding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">UnifyThreadBinding</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.UnifyThreadBinding" title="tvm.tir.transform.UnifyThreadBinding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">UnifyThreadBinding</span></code></a>()</p></td>
<td><p>Unify all the thread bindings for "blockIdx.x/y/z", "threadIdx.x/y/z", and "vthread.x/y/z".</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.UnrollLoop" title="tvm.tir.transform.UnrollLoop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">UnrollLoop</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.UnrollLoop" title="tvm.tir.transform.UnrollLoop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">UnrollLoop</span></code></a>()</p></td>
<td><p>Unroll the constant loop marked by unroll.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.VectorizeLoop" title="tvm.tir.transform.VectorizeLoop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">VectorizeLoop</span></code></a>([enable_vectorize])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.VectorizeLoop" title="tvm.tir.transform.VectorizeLoop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">VectorizeLoop</span></code></a>([enable_vectorize])</p></td>
<td><p>Lower vectorization loops.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.VerifyMemory" title="tvm.tir.transform.VerifyMemory"><code class="xref py py-obj docutils literal notranslate"><span class="pre">VerifyMemory</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.VerifyMemory" title="tvm.tir.transform.VerifyMemory"><code class="xref py py-obj docutils literal notranslate"><span class="pre">VerifyMemory</span></code></a>()</p></td>
<td><p>Verify if func contains illegal host side direct memory access.</p></td>
</tr>
</tbody>
@@ -7796,6 +7799,20 @@ with alloc_buffers at the allocation site.</p>
</dl>
</dd></dl>
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.transform.RemoveStoreUndef">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.transform.</span></span><span class="sig-name descname"><span class="pre">RemoveStoreUndef</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.transform.RemoveStoreUndef" title="Permalink to this definition">¶</a></dt>
+<dd><p>Remove stores of undefined values from the Stmt.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p><strong>fpass</strong> – The result pass</p>
+</dd>
+<dt class="field-even">Return type</dt>
+<dd class="field-even"><p><a class="reference internal" href="ir.html#tvm.transform.Pass" title="tvm.transform.Pass">tvm.transform.Pass</a></p>
+</dd>
+</dl>
+</dd></dl>
+
<dl class="py function">
<dt class="sig sig-object py" id="tvm.tir.transform.RemoveWeightLayoutRewriteBlock">
<span class="sig-prename descclassname"><span class="pre">tvm.tir.transform.</span></span><span class="sig-name descname"><span class="pre">RemoveWeightLayoutRewriteBlock</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.transform.RemoveWeightLayoutRewriteBlock" title="Permalink to this definition">¶</a></dt>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index a0e15167a..f37843d78 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/5821c1240/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 e7385f46d..12884448c 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/5821c1240/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 1e790735e..0c60e953e 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/5821c1240/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 f53bdb5d2..b776acb1e 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/5821c1240/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 e51c07e39..d252750cb 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/5821c1240/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 5f767d106..2b63a4041 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/5821c1240/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 6a1de1b33..346f0eae3 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/5821c1240/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 75c35cf59..74e047592 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/5821c1240/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 15757b88c..d8a89633a 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/5821c1240/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 054140bd1..3000a86fe 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/5821c1240/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 6f6d795cf..ceff68180 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/5821c1240/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 bbf4c35dd..5c9334446 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/5821c1240/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 8ae945d55..7b5354bdb 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/5821c1240/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 346372dba..67268426c 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/5821c1240/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 3bb2a4180..ee58d6b2e 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/5821c1240/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 6cad9cd8e..d3eb25956 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/5821c1240/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 262b70b52..77e79f9ce 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/5821c1240/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 5aa7635ac..8f35502ec 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/5821c1240/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 95bb92473..82e5682ac 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/5821c1240/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 555450bce..c4256593b 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/5821c1240/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 84cd9c53d..8802c6d19 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/5821c1240/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 4ac7979ca..09abaf9d8 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/5821c1240/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 ee8c931c4..a481212b1 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/5821c1240/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 38db6aec1..aa9c9230b 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/5821c1240/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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/5821c1240/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b4e36c61f/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 e5cc5a521..02a4b93ba 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 ec80e6974..79b59f013 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.869</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.359</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,7 +336,7 @@
</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>00:20.862</p></td>
+<td><p>00:21.352</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 6076fb70f..f870e5001 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.33s!
+resnet18_v1 inference graph built in 23.24s!
</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 0a30fe006..4e569961f 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.71s!
+yolov3-tiny inference graph built in 16.13s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 7c843c108..0bb5d2aed 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:29.426</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:32.954</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:47.352</p></td>
+<td><p>00:49.258</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:42.074</p></td>
+<td><p>00:43.696</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 bc74648a4..78f1e2bff 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.264</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.309</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.863</p></td>
+<td><p>00:02.890</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>00:00.401</p></td>
+<td><p>00:00.420</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 8c146cd11..c481b60e7 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.708</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.760</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.378</p></td>
+<td><p>00:00.405</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>00:00.330</p></td>
+<td><p>00:00.355</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 7118ab5e4..e3a68fa9d 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -479,9 +479,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
-</pre></div>
-</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -569,7 +566,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.343 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.390 ms
</pre></div>
</div>
</div>
@@ -643,7 +640,6 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.499 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 67376d687..ee2355134 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -668,16 +668,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.62/10.62 result: MeasureResult(costs=(0.025275727399999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.53354811668396, timestamp=1659739349.9832058) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.94/10.62 result: MeasureResult(costs=(0.0912391276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6082024574279785, timestamp=1659739352.1219757) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.89/11.89 result: MeasureResult(costs=(0.022570211200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5547225475311279, timestamp=1659739353.1586542) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.85/11.89 result: MeasureResult(costs=(0.1449266974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4410297870635986, timestamp=1659739356.1557446) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.69/11.89 result: MeasureResult(costs=(0.0727346324,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2974379062652588, timestamp=1659739357.5795963) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.79/11.89 result: MeasureResult(costs=(0.149680097,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5154078006744385, timestamp=1659739360.1345732) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.85/11.89 result: MeasureResult(costs=(0.3144699758,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.148500919342041, timestamp=1659739365.3292537) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.70/11.89 result: MeasureResult(costs=(0.025098832199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.582038402557373, timestamp=1659739365.9322722) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.64/11.89 result: MeasureResult(costs=(0.1640123738,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7210333347320557, timestamp=1659739368.7709506) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.67/11.89 result: MeasureResult(costs=(0.10047506580000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7173948287963867, timestamp=1659739370.5460224) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.05/10.05 result: MeasureResult(costs=(0.026717386599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5640602111816406, timestamp=1659967076.6930473) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.48/10.05 result: MeasureResult(costs=(0.10827101720000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.883862018585205, timestamp=1659967078.5899565) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.86/11.86 result: MeasureResult(costs=(0.0226247516,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5538632869720459, timestamp=1659967079.6540565) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.50/11.86 result: MeasureResult(costs=(0.178400016,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9779956340789795, timestamp=1659967083.2104225) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.69/11.86 result: MeasureResult(costs=(0.07283091859999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3083000183105469, timestamp=1659967085.1874716) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.76/11.86 result: MeasureResult(costs=(0.152874479,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6069319248199463, timestamp=1659967087.837515) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.86/11.86 result: MeasureResult(costs=(0.3123082974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.118847608566284, timestamp=1659967092.9983103) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.66/11.86 result: MeasureResult(costs=(0.025182184000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5502698421478271, timestamp=1659967093.564595) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.90/11.86 result: MeasureResult(costs=(0.1414735514,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3619203567504883, timestamp=1659967096.0469153) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.65/11.86 result: MeasureResult(costs=(0.10120940599999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7281930446624756, timestamp=1659967097.8335054) [('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 4be6331e8..29b7fa2e4 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -550,7 +550,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 492.02085444000204, 'median': 492.04294385001504, 'std': 0.35129703142693447}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 492.61969794000834, 'median': 492.56748635002623, 'std': 0.5595512100441674}
</pre></div>
</div>
</div>
@@ -705,178 +705,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.30/ 17.30 GFLOPS | Progress: (4/20) | 6.28 s
-[Task 1/25] Current/Best: 6.16/ 17.30 GFLOPS | Progress: (8/20) | 9.26 s
-[Task 1/25] Current/Best: 11.57/ 22.81 GFLOPS | Progress: (12/20) | 11.73 s
-[Task 1/25] Current/Best: 16.86/ 22.86 GFLOPS | Progress: (16/20) | 13.40 s
-[Task 1/25] Current/Best: 11.63/ 23.88 GFLOPS | Progress: (20/20) | 15.14 s Done.
+[Task 1/25] Current/Best: 17.53/ 17.53 GFLOPS | Progress: (4/20) | 6.32 s
+[Task 1/25] Current/Best: 6.15/ 17.53 GFLOPS | Progress: (8/20) | 9.35 s
+[Task 1/25] Current/Best: 11.54/ 22.70 GFLOPS | Progress: (12/20) | 11.86 s
+[Task 1/25] Current/Best: 16.83/ 22.70 GFLOPS | Progress: (16/20) | 13.55 s
+[Task 1/25] Current/Best: 11.57/ 23.73 GFLOPS | Progress: (20/20) | 15.29 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/ 12.78 GFLOPS | Progress: (4/20) | 3.90 s
-[Task 2/25] Current/Best: 14.04/ 17.63 GFLOPS | Progress: (8/20) | 5.18 s
-[Task 2/25] Current/Best: 21.08/ 21.08 GFLOPS | Progress: (12/20) | 6.51 s
-[Task 2/25] Current/Best: 12.74/ 21.08 GFLOPS | Progress: (16/20) | 7.81 s
-[Task 2/25] Current/Best: 20.19/ 21.08 GFLOPS | Progress: (20/20) | 9.40 s Done.
+[Task 2/25] Current/Best: 12.29/ 12.93 GFLOPS | Progress: (4/20) | 3.92 s
+[Task 2/25] Current/Best: 13.94/ 17.84 GFLOPS | Progress: (8/20) | 5.25 s
+[Task 2/25] Current/Best: 20.88/ 20.88 GFLOPS | Progress: (12/20) | 6.60 s
+[Task 2/25] Current/Best: 12.01/ 20.88 GFLOPS | Progress: (16/20) | 7.86 s
+[Task 2/25] Current/Best: 19.31/ 20.88 GFLOPS | Progress: (20/20) | 9.48 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/ 10.60 GFLOPS | Progress: (4/20) | 5.86 s
-[Task 3/25] Current/Best: 15.60/ 16.91 GFLOPS | Progress: (8/20) | 7.79 s
-[Task 3/25] Current/Best: 14.92/ 16.91 GFLOPS | Progress: (12/20) | 9.50 s
-[Task 3/25] Current/Best: 7.15/ 23.55 GFLOPS | Progress: (16/20) | 11.42 s
-[Task 3/25] Current/Best: 12.60/ 23.55 GFLOPS | Progress: (20/20) | 16.02 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.56 GFLOPS | Progress: (4/20) | 5.89 s
+[Task 3/25] Current/Best: 15.60/ 16.89 GFLOPS | Progress: (8/20) | 7.81 s
+[Task 3/25] Current/Best: 14.93/ 16.89 GFLOPS | Progress: (12/20) | 9.55 s
+[Task 3/25] Current/Best: 7.24/ 23.78 GFLOPS | Progress: (16/20) | 11.45 s
+[Task 3/25] Current/Best: 12.55/ 23.78 GFLOPS | Progress: (20/20) | 16.01 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.56/ 20.47 GFLOPS | Progress: (4/20) | 2.37 s
-[Task 4/25] Current/Best: 6.84/ 20.47 GFLOPS | Progress: (8/20) | 7.08 s
-[Task 4/25] Current/Best: 22.59/ 22.59 GFLOPS | Progress: (12/20) | 12.11 s
-[Task 4/25] Current/Best: 15.43/ 22.59 GFLOPS | Progress: (16/20) | 14.54 s
-[Task 4/25] Current/Best: 13.57/ 22.59 GFLOPS | Progress: (20/20) | 16.59 s Done.
+[Task 4/25] Current/Best: 9.53/ 20.50 GFLOPS | Progress: (4/20) | 2.41 s
+[Task 4/25] Current/Best: 6.66/ 20.50 GFLOPS | Progress: (8/20) | 7.14 s
+[Task 4/25] Current/Best: 22.21/ 22.21 GFLOPS | Progress: (12/20) | 12.07 s
+[Task 4/25] Current/Best: 16.79/ 22.21 GFLOPS | Progress: (16/20) | 14.46 s
+[Task 4/25] Current/Best: 13.21/ 22.21 GFLOPS | Progress: (20/20) | 16.56 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.73/ 10.48 GFLOPS | Progress: (4/20) | 2.59 s
-[Task 5/25] Current/Best: 11.69/ 12.88 GFLOPS | Progress: (8/20) | 4.67 s
-[Task 5/25] Current/Best: 11.82/ 18.13 GFLOPS | Progress: (12/20) | 7.86 s
-[Task 5/25] Current/Best: 11.66/ 22.64 GFLOPS | Progress: (16/20) | 9.25 s
-[Task 5/25] Current/Best: 12.00/ 22.64 GFLOPS | Progress: (20/20) | 11.12 s Done.
+[Task 5/25] Current/Best: 9.39/ 10.35 GFLOPS | Progress: (4/20) | 2.62 s
+[Task 5/25] Current/Best: 11.79/ 12.79 GFLOPS | Progress: (8/20) | 4.68 s
+[Task 5/25] Current/Best: 11.09/ 18.08 GFLOPS | Progress: (12/20) | 7.90 s
+[Task 5/25] Current/Best: 11.87/ 22.72 GFLOPS | Progress: (16/20) | 9.33 s
+[Task 5/25] Current/Best: 11.90/ 22.72 GFLOPS | Progress: (20/20) | 11.30 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.20/ 20.70 GFLOPS | Progress: (4/20) | 4.12 s
-[Task 6/25] Current/Best: 19.01/ 20.70 GFLOPS | Progress: (8/20) | 5.87 s
... 487 lines suppressed ...