You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/07/25 09:34:55 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@4d84620d07630f84c60b9386484ab2d8c102a0fe)
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 99af7c0fb deploying docs (apache/tvm@4d84620d07630f84c60b9386484ab2d8c102a0fe)
99af7c0fb is described below
commit 99af7c0fbbe0017fab2b2583b2517c65ee3a5d28
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Jul 25 09:34:49 2022 +0000
deploying docs (apache/tvm@4d84620d07630f84c60b9386484ab2d8c102a0fe)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 16 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1834 +++++++++++++++++++-
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 188 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 12 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 7 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 46 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 5 +-
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 | 20 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1834 +++++++++++++++++++-
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 188 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 12 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/doxygen/array_8h__dep__incl.svg | 2 +-
docs/reference/api/doxygen/bias__add_8h__incl.svg | 2 +-
docs/reference/api/doxygen/broadcast_8h__incl.svg | 2 +-
.../api/doxygen/constant__utils_8h__incl.svg | 2 +-
.../api/doxygen/constant__utils_8h_source.html | 2 +-
.../api/doxygen/detail_2broadcast_8h__incl.svg | 2 +-
.../api/doxygen/diagnostic_8h__dep__incl.svg | 2 +-
.../dir_72c2f11201cd7636dc7624de0754daa5.html | 2 +-
docs/reference/api/doxygen/einsum_8h__incl.svg | 2 +-
docs/reference/api/doxygen/error_8h__dep__incl.svg | 2 +-
docs/reference/api/doxygen/files.html | 2 +-
docs/reference/api/doxygen/flatten_8h__incl.svg | 2 +-
.../api/doxygen/functor_8h__dep__incl.svg | 2 +-
.../api/doxygen/instrument_8h__dep__incl.svg | 2 +-
.../api/doxygen/ir_2adt_8h__dep__incl.svg | 2 +-
.../api/doxygen/ir_2function_8h__dep__incl.svg | 2 +-
.../api/doxygen/ir_2module_8h__dep__incl.svg | 2 +-
.../api/doxygen/ir_2transform_8h__dep__incl.svg | 2 +-
docs/reference/api/doxygen/map_8h__dep__incl.svg | 2 +-
.../api/doxygen/namespacemembers_func_v.html | 3 +
docs/reference/api/doxygen/namespacemembers_v.html | 3 +
.../reference/api/doxygen/namespacetvm_1_1tir.html | 44 +
docs/reference/api/doxygen/nn_2bnn_8h__incl.svg | 2 +-
.../reference/api/doxygen/nn_2pooling_8h__incl.svg | 2 +-
.../reference/api/doxygen/nn_2softmax_8h__incl.svg | 2 +-
.../api/doxygen/optional_8h__dep__incl.svg | 2 +-
docs/reference/api/doxygen/reduction_8h__incl.svg | 2 +-
docs/reference/api/doxygen/reorg_8h__incl.svg | 2 +-
.../runtime_2container_2adt_8h__dep__incl.svg | 2 +-
docs/reference/api/doxygen/search/all_14.js | 2 +-
docs/reference/api/doxygen/search/all_17.js | 1 +
docs/reference/api/doxygen/search/functions_16.js | 1 +
.../api/doxygen/source__map_8h__dep__incl.svg | 2 +-
docs/reference/api/doxygen/stmt_8h__dep__incl.svg | 2 +-
.../api/doxygen/strided__slice_8h__incl.svg | 2 +-
docs/reference/api/doxygen/tir_2analysis_8h.html | 7 +-
.../api/doxygen/tir_2analysis_8h_source.html | 3 +-
.../api/doxygen/tir_2expr_8h__dep__incl.svg | 2 +-
.../api/doxygen/tir_2function_8h__dep__incl.svg | 2 +-
.../doxygen/tir_2op__attr__types_8h__dep__incl.svg | 2 +-
docs/reference/api/doxygen/topi_2nn_8h__incl.svg | 2 +-
.../api/doxygen/topi_2transform_8h__incl.svg | 2 +-
docs/reference/api/doxygen/var_8h__dep__incl.svg | 2 +-
docs/reference/api/doxygen/with_8h__dep__incl.svg | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/tir.html | 28 +
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 3 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 28 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
166 files changed, 4618 insertions(+), 1194 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 3249599ee..977630e85 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 0.258 seconds)
+ **Total running time of the script:** ( 1 minutes 3.708 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 b0240e528..ae04013be 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.zip16b432e1-3333-4845-8e3e-11d93a3c8c8a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip59aa3dc7-ad17-4fe9-95fa-cc3cec82a515 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 9373db373..79eb381c5 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 46.8MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 52.2MB/s]
57%|#####7 | 23.7M/41.5M [00:00<00:00, 61.9MB/s]
72%|#######2 | 29.9M/41.5M [00:00<00:00, 53.2MB/s]
85%|########4 | 35.2M/41.5M [00:00<00:00, 49.9MB/s]
97%|#########6| 40.2M/41.5M [00:00<00:00, 45.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 51.0MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 45.6MB/s]
26%|##5 | 10.7M/41.5M [00:00<00:01, 30.5MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 32.2MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 41.6MB/s]
64%|######4 | 26.7M/41.5M [00:00<00:00, 40.0MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 44.2MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 49.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 42.5MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index e30a59136..8ef7d2cb2 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]
45%|####4 | 19.9M/44.7M [00:00<00:00, 208MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 238MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
37%|###6 | 16.4M/44.7M [00:00<00:00, 172MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 245MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 234MB/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 0a6140a18..852fdfd44 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 3.865 seconds)
+ **Total running time of the script:** ( 1 minutes 5.949 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 6711fda5c..976d19e15 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
=================
-**04:58.391** total execution time for **how_to_compile_models** files:
+**05:07.424** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:03.865 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.949 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:00.258 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.708 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.973 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.806 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.307 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.924 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.719 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.505 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.741 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.611 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.571 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.035 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.536 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.491 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.478 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.694 | 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 6c783e17d..64ff95515 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)
- 14.9003 14.8616 15.2206 14.6544 0.1842
+ 16.5191 16.7597 16.9627 15.9348 0.4137
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 02c4527c0..1acf39306 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.42M/170M [00:00<00:03, 46.3MB/s]
5%|5 | 8.84M/170M [00:00<00:03, 44.6MB/s]
18%|#8 | 30.9M/170M [00:00<00:01, 128MB/s]
32%|###1 | 53.7M/170M [00:00<00:00, 171MB/s]
45%|####5 | 77.2M/170M [00:00<00:00, 198MB/s]
60%|#####9 | 101M/170M [00:00<00:00, 216MB/s]
74%|#######3 | 125M/170M [00:00<00:00, 227MB/s]
87%|########7 | 149M/170M [00:00<00:00, 234MB/s]
100%|##########| 170M/170M [00:00<00:00, 199MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.31M/170M [00:00<00:03, 45.1MB/s]
5%|5 | 8.62M/170M [00:00<00:03, 45.1MB/s]
18%|#8 | 31.2M/170M [00:00<00:01, 132MB/s]
34%|###3 | 56.9M/170M [00:00<00:00, 187MB/s]
49%|####8 | 83.2M/170M [00:00<00:00, 219MB/s]
64%|######4 | 109M/170M [00:00<00:00, 237MB/s]
80%|#######9 | 136M/170M [00:00<00:00, 250MB/s]
95%|#########5| 162M/170M [00:00<00:00, 258MB/s]
100%|##########| 170M/170M [00:00<00:00, 213MB/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 50.323 seconds)
+ **Total running time of the script:** ( 2 minutes 59.282 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 6dfaf9d0a..72a6771ac 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]
22%|##2 | 3.01M/13.6M [00:00<00:00, 31.4MB/s]
54%|#####4 | 7.35M/13.6M [00:00<00:00, 39.7MB/s]
82%|########2 | 11.1M/13.6M [00:00<00:00, 38.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 34.4MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 165MB/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)
- 90.2637 90.2283 90.7898 90.1207 0.1206
+ 90.4430 90.2965 98.7597 90.0577 0.8683
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.926 seconds)
+ **Total running time of the script:** ( 1 minutes 9.232 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 6141251d8..927af7c2d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.9349 119.9135 121.7696 119.1089 0.3718
+ 120.4985 120.4603 121.6484 119.7529 0.3493
@@ -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 59.048 seconds)
+ **Total running time of the script:** ( 1 minutes 51.939 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 d42cadb93..996610421 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 22.533 seconds)
+ **Total running time of the script:** ( 1 minutes 26.756 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 3c5d8b7b7..37da200af 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 | 6829/132723 [00:00<00:01, 68284.86KB/s]
12%|#1 | 15636/132723 [00:00<00:01, 79920.39KB/s]
18%|#8 | 24396/132723 [00:00<00:01, 83422.71KB/s]
25%|##5 | 33274/132723 [00:00<00:01, 85535.14KB/s]
32%|###1 | 41950/132723 [00:00<00:01, 85973.96KB/s]
38%|###8 | 50685/132723 [00:00<00:00, 86440.20KB/s]
45%|####4 | 59330/132723 [00:00<00:00, 86434.41KB/s]
51%|#####1 | 68051/132723 [00:00<00:00, 86678.23KB/s]
58%|#####7 | 76822/132723 [00:00<00:00, 86999.67KB/s]
65%|######4 | 85631/132723 [00:01<00:00, 87334.93KB/s]
71%|#######1 | 94401/132723 [00:01<00:00, 87442.72KB/s]
78%|#######7 | 103189/132723 [00:01<00:00, 87566.93KB/s]
84%|########4 | 111950/132723 [00:01<00:00, 87576.84KB/s]
91%|######### | 120708/132723 [00:01<00:00, 81909.07KB/s]
97%|#########7| 128973/132723 [00:01<00:00, 81810.65KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84615.14KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5270/132723 [00:00<00:02, 52694.52KB/s]
9%|9 | 12371/132723 [00:00<00:01, 63465.06KB/s]
15%|#4 | 19324/132723 [00:00<00:01, 66222.59KB/s]
20%|#9 | 26342/132723 [00:00<00:01, 67782.45KB/s]
25%|##5 | 33552/132723 [00:00<00:01, 69332.75KB/s]
31%|### | 40831/132723 [00:00<00:01, 70505.57KB/s]
37%|###6 | 48620/132723 [00:00<00:01, 72916.34KB/s]
42%|####2 | 56284/132723 [00:00<00:01, 74098.46KB/s]
48%|####8 | 63878/132723 [00:00<00:00, 74671.11KB/s]
54%|#####3 | 71496/132723 [00:01<00:00, 75131.55KB/s]
60%|#####9 | 79221/132723 [00:01<00:00, 75777.03KB/s]
65%|######5 | 86799/132723 [00:01<00:00, 72518.23KB/s]
71%|#######1 | 94452/132723 [00:01<00:00, 73694.64KB/s]
77%|#######6 | 101846/132723 [00:01<00:00, 70504.69KB/s]
82%|########2 | 109261/132723 [00:01<00:00, 71523.61KB/s]
88%|########7
| 116447/132723 [00:01<00:00, 58494.50KB/s]
93%|#########2| 123306/132723 [00:01<00:00, 61008.78KB/s]
99%|#########8| 130875/132723 [00:01<00:00, 64908.82KB/s]
100%|##########| 132723/132723 [00:01<00:00, 68716.90KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 27.845 seconds)
+ **Total running time of the script:** ( 2 minutes 33.482 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 f92094ed1..7da35cf20 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**10:38.371** total execution time for **how_to_deploy_models** files:
+**10:53.218** 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``) | 02:50.323 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:59.282 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:27.845 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:33.482 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:59.048 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:51.939 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:22.533 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:26.756 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.926 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:09.232 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.375 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.174 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.316 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.345 | 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 19a7537c2..00c1298dd 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.zipe46d9a07-b21d-4c1a-b954-2eb430b5e322 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip4a8c9ac6-92ed-4e7a-a51b-246237330719 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 35089d47b..18c72ba7c 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
=================
-**00:39.409** total execution time for **how_to_extend_tvm** files:
+**00:41.026** 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``) | 00:35.963 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.849 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.160 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.225 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.278 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.944 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 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 cacc48142..643bbbeb3 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: 6713us [6713us] (45.89%; 45.89%)
- FoldScaleAxis: 7915us [6us] (54.11%; 54.11%)
- FoldConstant: 7909us [1599us] (54.07%; 99.92%)
- InferType: 6310us [6310us] (43.14%; 79.78%)
+ InferType: 6853us [6853us] (45.71%; 45.71%)
+ FoldScaleAxis: 8139us [7us] (54.29%; 54.29%)
+ FoldConstant: 8132us [1638us] (54.24%; 99.91%)
+ InferType: 6494us [6494us] (43.32%; 79.86%)
@@ -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: 6207us [6207us] (44.88%; 44.88%)
- FoldScaleAxis: 7624us [4us] (55.12%; 55.12%)
- FoldConstant: 7620us [1569us] (55.09%; 99.94%)
- InferType: 6051us [6051us] (43.75%; 79.41%)
+ InferType: 6409us [6409us] (44.75%; 44.75%)
+ FoldScaleAxis: 7912us [6us] (55.25%; 55.25%)
+ FoldConstant: 7906us [1638us] (55.21%; 99.93%)
+ InferType: 6269us [6269us] (43.77%; 79.29%)
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 7ca49e00c..7cc72d945 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: 54.184629 ms
+ Convolution: 54.154645 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 8de54e304..5f6e6dc68 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: 6.604075 ms
+ conv2d with tensor core: 7.209038 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 1b718ffee..4cd3d548f 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: 0.016583
- Baseline: 3.338442
+ Numpy running time: 0.019116
+ Baseline: 3.288668
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.291724
+ Opt1: 0.302890
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.330800
+ Opt2: 0.338207
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.115487
+ Opt3: 0.116099
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110545
+ Opt4: 0.111929
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111262
+ Opt5: 0.112543
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.144914
+ Opt6: 0.145124
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 ccca6158b..16785c85f 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
=================
-**00:33.877** total execution time for **how_to_optimize_operators** files:
+**00:34.221** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.564 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.938 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.242 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.211 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.071 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.072 | 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 e3b4fb862..f674621fa 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
=================
-**05:52.334** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:59.135** 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``) | 03:10.868 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:13.653 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.519 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.581 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:44.791 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.201 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.115 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.040 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.552 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.849 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.488 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.812 | 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 94c6bdb83..67d0d8139 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
@@ -240,54 +240,896 @@ 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" = 112;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [36]), storage_scope = shared;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 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
- for (rc.outer.outer: int32, 0, 128) {
- for (ry.outer.outer: int32, 0, 3) {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 4) {
- if @tir.likely((threadIdx.x_1 < 9), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [36], [], scope="shared")[((threadIdx.x_1*4) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = @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) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s), 9))) && (floormod(((threadIdx.x_1*4) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s), 9) < 8)), data[((((((rc.outer.outer*196) [...]
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_1: int32 = (rc.outer.outer*392)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= floormod(threadIdx.x_1, 63)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 49), 63)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 35), 63)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 21), 63)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 7), 63)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[(threadIdx.x_2*36)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 9)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 10)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 11)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 18)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 7)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 19)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 8)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 20)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 27)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 10)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 28)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 11)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 29)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 12)] = kernel[((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 13)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 14)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 15)] = kernel[((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 16)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 17)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 18)] = kernel[((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 19)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 20)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 21)] = kernel[((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 22)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 23)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4608)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 25)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4609)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 26)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4610)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4617)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 28)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4618)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 29)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4619)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4626)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 31)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4627)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 32)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4628)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 33)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4635)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 34)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4636)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 35)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4637)]
}
}
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 12) {
- let cse_var_1: int32 = (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + threadIdx.x_2)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (floordiv((cse_var_1 + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod((cse_var_1 + threadIdx.x_2), 12), 3)*9)) + (ry.outer.outer*3)) + floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 4), 9)) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 1)], 0f32, dtype=float32)
}
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 4) {
- let cse_var_2: int32 = ((rc.inner*9) + rx.outer.inner)
- {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_2]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(cse_var_2 + 1)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(cse_var_2 + 2)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(cse_var_2 + 3)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(cse_var_2 + 4)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(cse_var_2 + 5)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_2 + 6)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2*36)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 12)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 13)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 14)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 21)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 7)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 22)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 8)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 23)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 30)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 10)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 31)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 11)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 32)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 13)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 14)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 16)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 17)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 19)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 20)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 22)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 23)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4611)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 25)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4612)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 26)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4613)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4620)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 28)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4621)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 29)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4622)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4629)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 31)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4630)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 32)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4631)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 33)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4638)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 34)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4639)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 35)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4640)]
+ }
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((floormod(threadIdx.x_1, 63) < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 49), 63) < 54) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 35), 63) < 54) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 21), 63) < 54) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 7), 63) < 54) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) + 6)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2*36)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 15)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 16)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 17)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 24)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 7)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 25)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 8)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 26)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 33)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 10)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 34)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 11)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 35)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 13)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 14)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 16)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 17)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 19)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 20)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 22)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 23)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4614)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 25)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4615)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 26)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4616)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4623)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 28)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4624)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 29)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4625)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4632)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 31)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4633)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 32)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4634)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 33)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4641)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 34)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4642)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 35)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4643)]
}
}
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
}
}
- compute[(((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
+ }
}
}
@@ -341,7 +1183,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.301 ms
+ Execution time of this operator: 0.283 ms
@@ -391,18 +1233,18 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
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=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
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)
@@ -412,14 +1254,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -436,16 +1278,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=36)
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=32)
+ 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=112)
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=32)
+ 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=112)
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", 0)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -463,9 +1305,9 @@ 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__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[36];
+ __shared__ float pad_temp_shared[504];
__shared__ float kernel_shared[384];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -474,38 +1316,866 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 4; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- if (((int)threadIdx.x) < 9) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) % 9))) && ((((((int)threadIdx.x) * 4) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + ax0_ax1_fused_ax2_fused_ax3_fused_inner [...]
- }
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 12; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + ((int)threadIdx.x))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 36)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx.x)) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3))];
- }
- __syncthreads();
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_inner * 9) + rx_outer_inner)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 1)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 2)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 3)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 4)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 5)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 6)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- }
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((9 <= ((((int)threadIdx.x) + 49) % 63)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((9 <= ((((int)threadIdx.x) + 21) % 63)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = ((((2 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[(((int)threadIdx.x) * 36)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 2)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 9)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 10)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 11)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 18)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 19)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 20)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 27)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 28)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 29)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 12)] = kernel[((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 2)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 15)] = kernel[((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 16)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 17)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 2)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 18)] = kernel[((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 19)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 20)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 2)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 21)] = kernel[((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 22)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 23)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 2)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4608)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 25)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4609)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 26)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4610)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4617)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 28)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4618)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 29)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4619)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4626)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 31)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4627)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 32)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4628)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 33)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4635)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 34)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4636)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 35)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4637)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 1)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[(((int)threadIdx.x) * 36)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 5)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 12)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 13)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 14)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 21)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 22)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 23)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 30)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 31)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 32)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 5)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 16)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 17)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 5)];
}
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 19)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 20)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 5)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 22)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 23)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 5)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4611)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 25)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4612)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 26)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4613)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4620)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 28)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4621)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 29)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4622)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4629)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 31)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4630)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 32)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4631)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 33)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4638)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 34)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4639)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 35)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4640)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((((((int)threadIdx.x) + 49) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((((((int)threadIdx.x) + 21) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) + 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[(((int)threadIdx.x) * 36)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 8)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 15)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 16)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 17)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 24)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 25)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 26)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 33)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 34)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 35)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 8)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 16)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 17)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 8)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 19)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 20)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 8)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 22)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 23)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 8)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4614)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 25)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4615)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 26)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4616)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4623)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 28)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4624)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 29)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4625)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4632)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 31)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4633)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 32)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4634)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 33)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4641)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 34)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4642)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 35)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4643)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ }
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
- compute[((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
}
@@ -566,7 +2236,7 @@ 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 10.868 seconds)
+ **Total running time of the script:** ( 3 minutes 13.653 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 a37a65e78..d38bcb8cd 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)
- 9.7756 9.8054 9.8215 9.6998 0.0540
+ 9.8781 9.8723 9.9210 9.8409 0.0330
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 46e875a0f..6d0eb21c9 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)
- 750.1576 750.3181 750.4153 749.7394 0.2984
+ 763.8140 763.9690 766.1337 761.3394 1.9603
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.519 seconds)
+ **Total running time of the script:** ( 1 minutes 22.581 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 71b0c3cee..b05cf6394 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
@@ -397,103 +397,105 @@ 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_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [256], [])[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_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
{
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_4: int32 = (i.inner*16)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_5: int32 = ((i.inner*16) + 1)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_6: int32 = ((i.inner*16) + 2)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_7: int32 = ((i.inner*16) + 3)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_8: int32 = ((i.inner*16) + 4)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_9: int32 = ((i.inner*16) + 5)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_10: int32 = ((i.inner*16) + 6)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_11: int32 = ((i.inner*16) + 7)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_12: int32 = ((i.inner*16) + 8)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_13: int32 = ((i.inner*16) + 9)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_14: int32 = ((i.inner*16) + 10)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_15: int32 = ((i.inner*16) + 11)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_16: int32 = ((i.inner*16) + 12)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_17: int32 = ((i.inner*16) + 13)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_18: int32 = ((i.inner*16) + 14)
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_19: int32 = ((i.inner*16) + 15)
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ compute_5: Buffer(compute_4, float32, [1024], [])[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_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 32) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ {
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*512) + (i.inner*16))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
@@ -550,7 +552,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.801 ms
+ Execution time of this operator: 2.226 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 936a75abc..e96af1298 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:46.633** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.263** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.597 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.228 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 920cda8f2..6410bc48d 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: 221.29/221.29 result: MeasureResult(costs=(0.0010461413241379311,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8990349769592285, timestamp=1658702222.4748678) [('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: 0.00/221.29 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 188.66/188.66 result: MeasureResult(costs=(0.0012271131666666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0360028743743896, timestamp=1658735941.8228946) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/188.66 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: 261.75/261.75 result: MeasureResult(costs=(0.0008844501428571427,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6992511749267578, timestamp=1658702223.3393252) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 261.65/261.65 result: MeasureResult(costs=(0.0008847866740331492,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7377474308013916, timestamp=1658735942.7469308) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 0.00/261.75 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 0.00/261.75 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 5.31/261.75 result: MeasureResult(costs=(0.04361735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.843292236328125, timestamp=1658702227.9198248) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.34/261.75 result: MeasureResult(costs=(0.06940382975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.573373317718506, timestamp=1658702229.159794) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.30/261.65 result: MeasureResult(costs=(0.0436847795,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8295247554779053, timestamp=1658735947.3164046) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/261.65 result: MeasureResult(costs=(0.06936260500000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.560149431228638, timestamp=1658735948.5655847) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.26/261.75 result: MeasureResult(costs=(0.008191259000000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3049187660217285, timestamp=1658702240.210737) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 27.29/261.65 result: MeasureResult(costs=(0.008483467529411766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3405115604400635, timestamp=1658735959.6776476) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 0.00/261.75 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 0.001227
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 ae1f21825..f5a652bc1 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 305.6 98.713 (1, 2, 10, 10, 3) 2 1 [305.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.971 0.96 (1, 6, 10, 10) 1 1 [2.971]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.012 0.327 (1, 1, 10, 10, 3) 1 1 [1.012]
- Total_time - 309.584 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.6 98.73 (1, 2, 10, 10, 3) 2 1 [309.6]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.027 0.965 (1, 6, 10, 10) 1 1 [3.027]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 0.305 (1, 1, 10, 10, 3) 1 1 [0.957]
+ Total_time - 313.584 - - - - -
@@ -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 216.9 98.633 (1, 1, 10, 10, 6) 2 1 [216.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.171 0.987 (1, 6, 10, 10) 1 1 [2.171]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.834 0.379 (1, 3, 10, 10, 1) 1 1 [0.834]
- Total_time - 219.905 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.75 96.659 (1, 6, 10, 10, 1) 2 1 [79.75]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.791 2.17 (1, 6, 10, 10) 1 1 [1.791]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.966 1.171 (1, 1, 10, 10, 3) 1 1 [0.966]
+ Total_time - 82.507 - - - - -
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 30227c340..4f9bf7e4b 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/tmp2gza993c/images/random'
+ '/tmp/tmp10k99h1i/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp2gza993c/images/target contains 8144 images
- /tmp/tmp2gza993c/images/random contains 5000 images
+ /tmp/tmp10k99h1i/images/target contains 8144 images
+ /tmp/tmp10k99h1i/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 53s - loss: 0.2120 - accuracy: 0.9264 - val_loss: 0.1517 - val_accuracy: 0.9585
+ 328/328 - 55s - loss: 0.2148 - accuracy: 0.9264 - val_loss: 0.1300 - val_accuracy: 0.9603
Epoch 2/3
- 328/328 - 50s - loss: 0.0935 - accuracy: 0.9625 - val_loss: 0.1181 - val_accuracy: 0.9622
+ 328/328 - 53s - loss: 0.1003 - accuracy: 0.9622 - val_loss: 0.1086 - val_accuracy: 0.9630
Epoch 3/3
- 328/328 - 50s - loss: 0.0671 - accuracy: 0.9744 - val_loss: 0.1533 - val_accuracy: 0.9543
+ 328/328 - 52s - loss: 0.0694 - accuracy: 0.9747 - val_loss: 0.1500 - val_accuracy: 0.9528
- <keras.callbacks.History object at 0x7fb2b22d0290>
+ <keras.callbacks.History object at 0x7fc0edf6f750>
@@ -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 35.825 seconds)
+ **Total running time of the script:** ( 5 minutes 11.006 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 2445e37e7..40ce60eba 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**05:21.306** total execution time for **how_to_work_with_microtvm** files:
+**05:58.197** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:35.825 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:11.006 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.211 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.830 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.268 | 0.0 MB |
-+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.359 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
++---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 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 84d9fc084..485e547a7 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:41.479** total execution time for **how_to_work_with_relay** files:
+**00:42.005** 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``) | 00:30.031 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.553 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.927 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.918 | 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_build_gcn.py` (``build_gcn.py``) | 00:01.528 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 14085cc02..dbfacf281 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 0x7fb2b3480320>
+ <function my_cuda_math_rule at 0x7fc056ded440>
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 87e4abdf3..6b9ae07c5 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**00:04.212** total execution time for **how_to_work_with_schedules** files:
+**00:04.193** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.931 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.959 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.037 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.975 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.537 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.546 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.528 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.532 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.101 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 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 047d616ad..d80140884 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/tmp1yhu0mby/input0.cc'\nsource_filename = \"/tmp/tmp1yhu0mby/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/tmpi56dcld2/input0.cc'\nsource_filename = \"/tmp/tmpi56dcld2/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 aa0ba5f3d..1a688481e 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
=================
-**00:20.831** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.911** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.825 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.905 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index dde5482d1..8c7a1536c 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 22.21s!
+ resnet18_v1 inference graph built in 23.50s!
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 4430103f4..8218570b0 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 15.64s!
+ yolov3-tiny inference graph built in 16.34s!
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 6d55b58db..48e9cf648 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
=================
-**01:30.383** total execution time for **topic_vta_tutorials_frontend** files:
+**01:33.177** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.090 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.265 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.293 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.912 | 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 b1ef1551a..bcaded668 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
=================
-**00:03.291** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.305** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.878 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.882 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.413 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.424 | 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 88a89dd2f..c2a6a7f97 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.748** total execution time for **topic_vta_tutorials** files:
+**00:00.756** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.397 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.406 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.351 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.350 | 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 d07b6d2f0..71b55d8e4 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 91.933 ms
+ Execution time of this operator: 94.517 ms
@@ -444,11 +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 13.660 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 995fc5fed..04737d325 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.93/9.93 result: MeasureResult(costs=(0.027020305799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.566795825958252, timestamp=1658701045.4004948) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.50/9.93 result: MeasureResult(costs=(0.10746353420000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8664262294769287, timestamp=1658701047.2827883) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.0226637174,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5552175045013428, timestamp=1658701048.3385143) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.84 result: MeasureResult(costs=(0.1448832136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4331634044647217, timestamp=1658701051.344736) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.70/11.84 result: MeasureResult(costs=(0.0724601834,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2928252220153809, timestamp=1658701052.7670085) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.79/11.84 result: MeasureResult(costs=(0.149610505,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.558471918106079, timestamp=1658701055.3665576) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.89/11.84 result: MeasureResult(costs=(0.30286826580000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.978031158447266, timestamp=1658701060.9070563) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.78/11.84 result: MeasureResult(costs=(0.024912430800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5406723022460938, timestamp=1658701061.468179) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.92/11.84 result: MeasureResult(costs=(0.1400510712,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3587682247161865, timestamp=1658701063.946186) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.80/11.84 result: MeasureResult(costs=(0.0960253134,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6489791870117188, timestamp=1658701065.6541831) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 8.75/8.75 result: MeasureResult(costs=(0.0306806152,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.625948429107666, timestamp=1658734760.8255267) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.37/8.75 result: MeasureResult(costs=(0.1134083578,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9627289772033691, timestamp=1658734762.805162) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.0226795324,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5672330856323242, timestamp=1658734763.8648155) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.62/11.84 result: MeasureResult(costs=(0.16582504839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7746224403381348, timestamp=1658734767.2120047) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.59/11.84 result: MeasureResult(costs=(0.0748106746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3436377048492432, timestamp=1658734768.6765792) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.80/11.84 result: MeasureResult(costs=(0.1491191014,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.510031223297119, timestamp=1658734771.7537613) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.77/11.84 result: MeasureResult(costs=(0.3473247812,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.670970916748047, timestamp=1658734777.4642808) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 9.84/11.84 result: MeasureResult(costs=(0.027271461799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.581989049911499, timestamp=1658734778.0656807) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.62/11.84 result: MeasureResult(costs=(0.16615526919999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7575185298919678, timestamp=1658734780.9418721) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.27/11.84 result: MeasureResult(costs=(0.1182859084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.997889757156372, timestamp=1658734782.9978788) [('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 73cb07ca6..746a49479 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': 475.11939588999667, 'median': 475.16727245019865, 'std': 0.4206919897508426}
+ {'mean': 495.14105112001744, 'median': 495.2042046500537, 'std': 1.0245270115578045}
@@ -563,30 +563,31 @@ 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: 19.04/ 19.04 GFLOPS | Progress: (4/20) | 5.71 s
[Task 1/25] Current/Best: 6.26/ 19.04 GFLOPS | Progress: (8/20) | 9.18 s
[Task 1/25] Current/Best: 11.71/ 23.06 GFLOPS | Progress: (12/20) | 11.64 s
[Task 1/25] Current/Best: 18.31/ 23.16 GFLOPS | Progress: (16/20) | 13.29 s
[Task 1/25] Current/Best: 11.69/ 24.27 GFLOPS | Progress: (20/20) | 15.03 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.42/ 13.17 GFLOPS | Progress: (4/20) | 3.72 s
[Task 2/25] Current/Best: 14.52/ 19.05 GFLOPS | Progress: (8/20) | 5.03 s
[Task 2/25] Current/Best: 21.18/ 21.18 GFLOPS | Progress: (12/20) | 6.35 s
[Task 2/25] Current/Best: 12.85/ 21.18 GFLOPS | Progress: (16/20) | 7.61 s
[Task 2/25] Current/Best: 19.72/ 21.18 GFLOPS | Progress: (20/20) | 9.21 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.65/ 10.75 GFLOPS | Progress: (4/20) | 5.77 s
[Task 3/25] Current/Best: 16.93/ 18.35 GFLOPS | Progress: (8/20) | 7.66 s
[Task 3/25] Current/Best: 16.22/ 18.35 GFLOPS | Progress: (12/20) | 9.33 s
[Task 3/25] Current/Best: 7.28/ 24.03 GFLOPS | Progress: (16/20) | 11.20 s
[Task 3/25] Current/Best: 12.91/ 24.03 GFLOPS | Progress: (20/20) | 15.76 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 19.56 GFLOPS | Progress: (4/20) | 2.38 s
[Task 4/25] Current/Best: 6.47/ 19.56 GFLOPS | Progress: (8/20) | 7.12 s
[Task 4/25] Current/Best: 22.27/ 22.27 GFLOPS | Progress: (12/20) | 12.05 s
[Task 4/25] Current/Best: 16.60/ 22.27 GFLOPS | Progress: (16/20) | 14.43 s
[Task 4/25] Current/Best: 13.71/ 22.27 GFLOPS | Progress: (20/20) | 16.46 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.80/ 10.53 GFLOPS | Progress: (4/20) | 2.56 s
[Task 5/25] Current/Best: 10.98/ 12.69 GFLOPS | Progress: (8/20) | 4.60 s
[Task 5/25] Current/Best: 11.80/ 18.37 GFLOPS | Progress: (12/20) | 7.63 s
[Task 5/25] Current/Best: 11.80/ 23.06 GFLOPS | Progress: (16/20) | 9.03 s
[Task 5/25] Current/Best: 12.26/ 23.06 GFLOPS | Progress: (20/20) | 10.94 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.46/ 21.06 GFLOPS | Progress: (4/20) | 4.06 s
[Task 6/25] Current/Best: 19.27/ 21.06 GFLOPS | Progress: (8/20) | 5.80 s
[Task 6/25] Current/Best: 13.51/ 21.06 GFLOPS | Progress: (12/20) | 7.74 s
[Task 6/25] Current/Best: 20.29/ 21.06 GFLOPS | Progress: (16/20) | 9.98 s
[Task 6/25] Current/Best: 3.77/ 21.06 GFLOPS | Progress: (20/20) | 12.47 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.43/ 13.28 GFLOPS | Progress: (4/20) | 3.59 s
[Task 7/25] Current/Best: 20.54/ 21.67 GFLOPS | Progress: (8/20) | 5.07 s
[Task 7/25] Current/Best: 16.35/ 21.67 GFLOPS | Progress: (12/20) | 6.96 s
[Task 7/25] Current/Best: 12.44/ 21.67 GFLOPS | Progress: (16/20) | 8.98 s
[Task 7/25] Current/Best: 6.42/ 22.04 GFLOPS | Progress: (20/20) | 11.40 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.81/ 14.02 GFLOPS | Progress: (4/20) | 2.92 s
[Task 8/25] Current/Best: 9.27/ 14.02 GFLOPS | Progress: (8/20) | 8.07 s
[Task 8/25] Current/Best: 12.77/ 14.02 GFLOPS | Progress: (12/20) | 14.46 s
[Task 8/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (16/20) | 16.55 s
[Task 8/25] Current/Best: 19.91/ 19.91 GFLOPS | Progress: (20/20) | 23.68 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.57/ 16.09 GFLOPS | Progress: (4/20) | 11.94 s
[Task 9/25] Current/Best: 23.85/ 23.85 GFLOPS | Progress: (8/20) | 13.72 s
[Task 9/25] Current/Best: 8.39/ 23.85 GFLOPS | Progress: (12/20) | 16.26 s
[Task 9/25] Current/Best: 18.21/ 23.85 GFLOPS | Progress: (16/20) | 19.01 s
[Task 9/25] Current/Best: 9.33/ 23.85 GFLOPS | Progress: (20/20) | 27.44 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (4/20) | 2.54 s
[Task 10/25] Current/Best: 15.69/ 18.46 GFLOPS | Progress: (8/20) | 4.19 s
[Task 10/25] Current/Best: 12.55/ 19.06 GFLOPS | Progress: (12/20) | 5.72 s
[Task 10/25] Current/Best: 19.23/ 20.69 GFLOPS | Progress: (16/20) | 6.82 s
[Task 10/25] Current/Best: 9.00/ 20.69 GFLOPS | Progress: (20/20
) | 8.36 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.61/ 19.75 GFLOPS | Progress: (4/20) | 3.34 s
[Task 11/25] Current/Best: 17.16/ 19.75 GFLOPS | Progress: (8/20) | 6.11 s
[Task 11/25] Current/Best: 18.50/ 19.75 GFLOPS | Progress: (12/20) | 8.17 s
[Task 11/25] Current/Best: 13.73/ 21.53 GFLOPS | Progress: (16/20) | 11.02 s
[Task 11/25] Current/Best: 19.75/ 21.93 GFLOPS | Progress: (20/20) | 13.11 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.33 GFLOPS | Progress: (4/20) | 5.73 s
[Task 12/25] Current/Best: 5.28/ 18.33 GFLOPS | Progress: (8/20) | 9.62 s
[Task 12/25] Current/Best: 19.20/ 20.33 GFLOPS | Progress: (12/20) | 11.59 s
[Task 12/25] Current/Best: 15.64/ 20.33 GFLOPS | Progress: (16/20) | 14.48 s
[Task 12/25] Current/Best: 15.27/ 20.33 GFLOPS | Progress: (20/20) | 16.38 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.89/ 18.76 GFLOPS | Progress: (4/20) | 3.69 s
[Task 13/25] Current/Best: 17.22/ 21.36 GFLOPS | Progress: (8/20) | 6.27 s
[Task 13/25] Current/Best: 19.94/ 22.11 GFLOPS | Progress: (12/20) | 9.23 s
[Task 13/25] Current/Best: 12.48/ 22.11 GFLOPS | Progress: (16/20) | 12.64 s
[Task 13/25] Current/Best: 18.82/ 22.11 GFLOPS | Progress: (20/20) | 14.97 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.89/ 13.89 GFLOPS | Progress: (4/20) | 3.38 s
[Task 14/25] Current/Best: 6.08/ 14.40 GFLOPS | Progress: (8/20) | 5.49 s
[Task 14/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (12/20) | 8.15 s
[Task 14/25] Current/Best: 16.60/ 20.56 GFLOPS | Progress: (16/20) | 9.79 s Done.
-
[Task 14/25] Current/Best: 17.33/ 20.56 GFLOPS | Progress: (20/20) | 11.52 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 17.49/ 17.92 GFLOPS | Progress: (4/20) | 2.67 s
[Task 15/25] Current/Best: 14.69/ 18.43 GFLOPS | Progress: (8/20) | 3.99 s
[Task 15/25] Current/Best: 10.55/ 22.61 GFLOPS | Progress: (12/20) | 6.26 s
[Task 15/25] Current/Best: 22.04/ 22.61 GFLOPS | Progress: (16/20) | 9.44 s
[Task 15/25] Current/Best: 9.82/ 22.61 GFLOPS | Progress: (20/20) | 10.44 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.99/ 20.99 GFLOPS | Progress: (4/20) | 2.94 s
[Task 16/25] Current/Best: 3.09/ 20.99 GFLOPS | Progress: (8/20) | 4.53 s
[Task 16/25] Current/Best: 20.04/ 20.99 GFLOPS | Progress: (12/20) | 5.73 s
[Task 16/25] Current/Best: 18.28/ 20.99 GFLOPS | Progress: (16/20) |
7.07 s
[Task 16/25] Current/Best: 10.38/ 22.95 GFLOPS | Progress: (20/20) | 9.19 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.27/ 19.23 GFLOPS | Progress: (4/20) | 4.75 s
[Task 17/25] Current/Best: 14.63/ 23.72 GFLOPS | Progress: (8/20) | 7.48 s
[Task 17/25] Current/Best: 18.31/ 23.72 GFLOPS | Progress: (12/20) | 9.50 s
[Task 17/25] Current/Best: 17.96/ 23.72 GFLOPS | Progress: (16/20) | 11.70 s
[Task 17/25] Current/Best: 10.21/ 23.72 GFLOPS | Progress: (20/20) | 13.79 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.46/ 18.35 GFLOPS | Progress: (4/20) | 3.75 s
[Task 18/25] Current/Best: 10.73/ 19.32 GFLOPS | Progress: (8/20) | 7.39 s
[Task 18/25] Current/Best: 19.51/ 19.51 GFLOPS | Progress: (12/20) | 9.29 s
[Task 18/25] Current/Best: 10.20/ 19.51 GFLOPS | Progress: (16/20) | 13.14 s
[Task 18/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (20/20) | 14.66 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.02/ 20.25 GFLOPS | Progress: (4/20) | 6.10 s
[Task 19/25] Current/Best: 2.61/ 20.25 GFLOPS | Progress: (8/20) | 9.45 s
[Task 19/25] Current/Best: 20.12/ 21.86 GFLOPS | Progress: (12/20) | 12.49 s
[Task 19/25] Current/Best: 14.85/ 21.86 GFLOPS | Progress: (16/20) | 15.53 s
[Task 19/25] Current/Best: 2.70/ 23.43 GFLOPS | Progress: (20/20) | 18.32 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.81/ 14.89 GFLOPS | Progress: (4/20) | 3.39 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 6.39 s
[Task 1/25] Current/Best: 6.16/ 17.41 GFLOPS | Progress: (8/20) | 9.41 s
[Task 1/25] Current/Best: 11.53/ 22.68 GFLOPS | Progress: (12/20) | 11.84 s
[Task 1/25] Current/Best: 16.67/ 22.69 GFLOPS | Progress: (16/20) | 13.54 s
[Task 1/25] Current/Best: 11.62/ 23.89 GFLOPS | Progress: (20/20) | 15.33 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.32/ 12.94 GFLOPS | Progress: (4/20) | 3.85 s
[Task 2/25] Current/Best: 14.19/ 18.13 GFLOPS | Progress: (8/20) | 5.18 s
[Task 2/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (12/20) | 6.49 s
[Task 2/25] Current/Best: 11.96/ 21.10 GFLOPS | Progress: (16/20) | 7.77 s
[Task 2/25] Current/Best: 18.21/ 21.10 GFLOPS | Progress: (20/20) | 9.37 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/ 10.54 GFLOPS | Progress: (4/20) | 5.87 s
[Task 3/25] Current/Best: 15.57/ 16.84 GFLOPS | Progress: (8/20) | 7.82 s
[Task 3/25] Current/Best: 14.90/ 16.84 GFLOPS | Progress: (12/20) | 9.53 s
[Task 3/25] Current/Best: 7.20/ 23.81 GFLOPS | Progress: (16/20) | 11.44 s
[Task 3/25] Current/Best: 12.55/ 23.81 GFLOPS | Progress: (20/20) | 15.96 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.54/ 20.43 GFLOPS | Progress: (4/20) | 2.38 s
[Task 4/25] Current/Best: 6.69/ 20.43 GFLOPS | Progress: (8/20) | 6.70 s
[Task 4/25] Current/Best: 21.90/ 21.90 GFLOPS | Progress: (12/20) | 11.29 s
[Task 4/25] Current/Best: 16.56/ 21.90 GFLOPS | Progress: (16/20) | 13.57 s
[Task 4/25] Current/Best: 13.22/ 21.90 GFLOPS | Progress: (20/20) | 15.49 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.71/ 10.41 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.88/ 12.74 GFLOPS | Progress: (8/20) | 4.68 s
[Task 5/25] Current/Best: 10.51/ 18.02 GFLOPS | Progress: (12/20) | 7.80 s
[Task 5/25] Current/Best: 11.83/ 22.78 GFLOPS | Progress: (16/20) | 9.22 s
[Task 5/25] Current/Best: 12.00/ 22.78 GFLOPS | Progress: (20/20) | 11.05 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.27/ 20.63 GFLOPS | Progress: (4/20) | 3.95 s
[Task 6/25] Current/Best: 18.88/ 20.63 GFLOPS | Progress: (8/20) | 5.70 s
[Task 6/25] Current/Best: 13.33/ 20.63 GFLOPS | Progress: (12/20) | 7.64 s
[Task 6/25] Current/Best: 19.75/ 20.63 GFLOPS | Progress: (16/20) | 9.89 s
[Task 6/25] Current/Best: 3.74/ 20.63 GFLOPS | Progress: (20/20) | 12.45 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.22/ 12.71 GFLOPS | Progress: (4/20) | 3.57 s
[Task 7/25] Current/Best: 20.31/ 21.10 GFLOPS | Progress: (8/20) | 5.08 s
[Task 7/25] Current/Best: 16.10/ 21.10 GFLOPS | Progress: (12/20) | 7.03 s
[Task 7/25] Current/Best: 12.26/ 21.10 GFLOPS | Progress: (16/20) | 9.08 s
[Task 7/25] Current/Best: 6.35/ 21.68 GFLOPS | Progress: (20/20) | 11.54 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.03/ 13.98 GFLOPS | Progress: (4/20) | 2.91 s
[Task 8/25] Current/Best: 9.81/ 13.98 GFLOPS | Progress: (8/20) | 7.65 s
[Task 8/25] Current/Best: 12.76/ 13.98 GFLOPS | Progress: (12/20) | 13.78 s
[Task 8/25] Current/Best: 18.73/ 18.73 GFLOPS | Progress: (16/20) | 15.89 s
[Task 8/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (20/20) | 22.38 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.39/ 15.43 GFLOPS | Progress: (4/20) | 11.92 s
[Task 9/25] Current/Best: 23.20/ 23.20 GFLOPS | Progress: (8/20) | 13.68 s
[Task 9/25] Current/Best: 8.05/ 23.20 GFLOPS | Progress: (12/20) | 16.06 s
[Task 9/25] Current/Best: 17.93/ 23.20 GFLOPS | Progress: (16/20) | 18.72 s
[Task 9/25] Current/Best: 9.21/ 23.20 GFLOPS | Progress: (20/20) | 26.29 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.54/ 18.54 GFLOPS | Progress: (4/20) | 2.59 s
[Task 10/25] Current/Best: 15.42/ 18.54 GFLOPS | Progress: (8/20) | 4.15 s
[Task 10/25] Current/Best: 12.61/ 18.96 GFLOPS | Progress: (12/20) | 5.68 s
[Task 10/25] Current/Best: 19.18/ 20.49 GFLOPS | Progress: (16/20) | 6.79 s
[Task 10/25] Current/Best: 8.86/ 20.49 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: 12.23/ 18.17 GFLOPS | Progress: (4/20) | 3.31 s
[Task 11/25] Current/Best: 15.80/ 18.17 GFLOPS | Progress: (8/20) | 6.05 s
[Task 11/25] Current/Best: 18.09/ 18.17 GFLOPS | Progress: (12/20) | 8.11 s
[Task 11/25] Current/Best: 13.44/ 21.19 GFLOPS | Progress: (16/20) | 10.92 s
[Task 11/25] Current/Best: 19.54/ 21.58 GFLOPS | Progress: (20/20) | 12.95 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.01 GFLOPS | Progress: (4/20) | 5.37 s
[Task 12/25] Current/Best: 5.23/ 18.01 GFLOPS | Progress: (8/20) | 9.04 s
[Task 12/25] Current/Best: 18.80/ 18.87 GFLOPS | Progress: (12/20) | 11.02 s
[Task 12/25] Current/Best: 15.43/ 18.87 GFLOPS | Progress: (16/20) | 13.79 s
[Task 12/25] Current/Best: 15.17/ 18.87 GFLOPS | Progress: (20/20) | 15.69 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.97/ 17.35 GFLOPS | Progress: (4/20) | 3.69 s
[Task 13/25] Current/Best: 15.92/ 20.96 GFLOPS | Progress: (8/20) | 6.11 s
[Task 13/25] Current/Best: 19.47/ 21.62 GFLOPS | Progress: (12/20) | 8.99 s
[Task 13/25] Current/Best: 12.23/ 21.62 GFLOPS | Progress: (16/20) | 12.41 s
[Task 13/25] Current/Best: 18.63/ 21.62 GFLOPS | Progress: (20/20) | 14.68 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (4/20) | 3.35 s
[Task 14/25] Current/Best: 6.10/ 13.64 GFLOPS | Progress: (8/20) | 5.53 s
[Task 14/25] Current/Best: 20.20/ 20.20 GFLOPS | Progress: (12/20) | 8.04 s
[Task 14/25] Current/Best: 17.34/ 20.20 GFLOPS | Progress: (16/20) | 9.71 s Done.
+
[Task 14/25] Current/Best: 17.32/ 20.20 GFLOPS | Progress: (20/20) | 11.43 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.18/ 17.52 GFLOPS | Progress: (4/20) | 2.72 s
[Task 15/25] Current/Best: 14.33/ 18.16 GFLOPS | Progress: (8/20) | 4.06 s
[Task 15/25] Current/Best: 10.39/ 22.06 GFLOPS | Progress: (12/20) | 6.13 s
[Task 15/25] Current/Best: 20.38/ 22.06 GFLOPS | Progress: (16/20) | 9.51 s
[Task 15/25] Current/Best: 9.67/ 22.06 GFLOPS | Progress: (20/20) | 10.53 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.35/ 19.35 GFLOPS | Progress: (4/20) | 3.01 s
[Task 16/25] Current/Best: 3.04/ 19.35 GFLOPS | Progress: (8/20) | 4.66 s
[Task 16/25] Current/Best: 18.99/ 19.47 GFLOPS | Progress: (12/20) | 5.89 s
[Task 16/25] Current/Best: 17.81/ 19.47 GFLOPS | Progress: (16/20) |
7.25 s
[Task 16/25] Current/Best: 9.99/ 20.13 GFLOPS | Progress: (20/20) | 9.33 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.81/ 18.80 GFLOPS | Progress: (4/20) | 4.73 s
[Task 17/25] Current/Best: 12.45/ 23.26 GFLOPS | Progress: (8/20) | 7.63 s
[Task 17/25] Current/Best: 16.89/ 23.26 GFLOPS | Progress: (12/20) | 9.68 s
[Task 17/25] Current/Best: 16.47/ 23.26 GFLOPS | Progress: (16/20) | 11.81 s
[Task 17/25] Current/Best: 10.02/ 23.26 GFLOPS | Progress: (20/20) | 13.94 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.07/ 17.85 GFLOPS | Progress: (4/20) | 3.74 s
[Task 18/25] Current/Best: 10.58/ 17.85 GFLOPS | Progress: (8/20) | 7.25 s
[Task 18/25] Current/Best: 18.97/ 18.97 GFLOPS | Progress: (12/20) | 9.18 s
[Task 18/25] Current/Best: 9.86/ 18.97 GFLOPS | Progress: (16/20) | 12.73 s
[Task 18/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (20/20) | 14.26 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.88/ 19.94 GFLOPS | Progress: (4/20) | 6.13 s
[Task 19/25] Current/Best: 2.61/ 19.94 GFLOPS | Progress: (8/20) | 9.38 s
[Task 19/25] Current/Best: 15.99/ 20.70 GFLOPS | Progress: (12/20) | 12.20 s
[Task 19/25] Current/Best: 13.66/ 21.71 GFLOPS | Progress: (16/20) | 15.01 s
[Task 19/25] Current/Best: 2.70/ 23.00 GFLOPS | Progress: (20/20) | 17.80 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.43/ 15.31 GFLOPS | Progress: (4/20) | 3.33 s Done.
Done.
-
[Task 20/25] Current/Best: 9.71/ 14.89 GFLOPS | Progress: (8/20) | 6.80 s
[Task 20/25] Current/Best: 2.31/ 16.61 GFLOPS | Progress: (12/20) | 10.73 s
[Task 20/25] Current/Best: 12.36/ 16.61 GFLOPS | Progress: (16/20) | 14.51 s
[Task 20/25] Current/Best: 12.35/ 22.25 GFLOPS | Progress: (20/20) | 16.62 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.71 GFLOPS | Progress: (4/20) | 3.28 s
[Task 21/25] Current/Best: 14.66/ 17.71 GFLOPS | Progress: (8/20) | 4.88 s
[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 7.02 s
[Task 21/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (16/20) | 10.56 s
[Task 21/25] Current/Best: 4.47/ 18.05 GFLOPS | Progress: (20/20) | 17.86 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.03 GFLOPS | Progress: (4/20
) | 2.68 s
[Task 22/25] Current/Best: 8.72/ 21.36 GFLOPS | Progress: (8/20) | 4.72 s
[Task 22/25] Current/Best: 19.91/ 21.36 GFLOPS | Progress: (12/20) | 7.14 s
[Task 22/25] Current/Best: 15.65/ 21.36 GFLOPS | Progress: (16/20) | 9.27 s
[Task 22/25] Current/Best: 13.99/ 21.36 GFLOPS | Progress: (20/20) | 10.93 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.50/ 20.77 GFLOPS | Progress: (4/20) | 3.25 s
[Task 23/25] Current/Best: 14.03/ 20.77 GFLOPS | Progress: (8/20) | 6.54 s
[Task 23/25] Current/Best: 21.04/ 21.71 GFLOPS | Progress: (12/20) | 8.40 s
[Task 23/25] Current/Best: 6.40/ 21.71 GFLOPS | Progress: (16/20) | 15.51 s
[Task 23/25] Current/Best: 7.99/ 21.71 GFLOPS | Progress: (20/20) | 19.75 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.55/ 8.55 GFLOPS | Progress: (4/20) | 11.79 s
[Task 24/25] Current/Best: 2.13/ 8.55 GFLOPS | Progress: (8/20) | 22.81 s
[Task 24/25] Current/Best: 4.50/ 8.55 GFLOPS | Progress: (12/20) | 34.33 s Done.
-
[Task 24/25] Current/Best: 6.12/ 8.84 GFLOPS | Progress: (16/20) | 40.04 s
[Task 24/25] Current/Best: 3.29/ 9.00 GFLOPS | Progress: (20/20) | 46.11 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/ 2.77 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 6.01/ 8.68 GFLOPS | Progress: (8/20) | 22.88 s
[Task 25/25] Current/Best: 5.95/ 8.68 GFLOPS | Progress: (12/20) | 34.16 s
[Task 25/25] Current/Best: 5.84/ 8.97 GFLOPS | Progress: (16/20) | 35.87 s
[Task 25/25] Current/Best: 2.85/ 9.40 GFLOPS | Progress: (20/20) | 46.53 s
+
[Task 20/25] Current/Best: 10.54/ 15.31 GFLOPS | Progress: (8/20) | 6.62 s
[Task 20/25] Current/Best: 2.32/ 16.42 GFLOPS | Progress: (12/20) | 10.55 s
[Task 20/25] Current/Best: 12.53/ 16.42 GFLOPS | Progress: (16/20) | 14.34 s
[Task 20/25] Current/Best: 13.45/ 21.41 GFLOPS | Progress: (20/20) | 16.46 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.72 GFLOPS | Progress: (4/20) | 3.24 s
[Task 21/25] Current/Best: 14.63/ 17.72 GFLOPS | Progress: (8/20) | 4.80 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 6.95 s
[Task 21/25] Current/Best: 17.44/ 17.72 GFLOPS | Progress: (16/20) | 10.42 s
[Task 21/25] Current/Best: 4.47/ 17.72 GFLOPS | Progress: (20/20) | 17.64 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.07 GFLOPS | Progress: (4/20
) | 2.70 s
[Task 22/25] Current/Best: 9.04/ 21.74 GFLOPS | Progress: (8/20) | 4.68 s
[Task 22/25] Current/Best: 20.04/ 21.74 GFLOPS | Progress: (12/20) | 7.00 s
[Task 22/25] Current/Best: 15.41/ 21.74 GFLOPS | Progress: (16/20) | 9.09 s
[Task 22/25] Current/Best: 14.76/ 21.74 GFLOPS | Progress: (20/20) | 10.82 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.39/ 20.17 GFLOPS | Progress: (4/20) | 3.28 s
[Task 23/25] Current/Best: 15.68/ 20.17 GFLOPS | Progress: (8/20) | 6.61 s
[Task 23/25] Current/Best: 20.74/ 21.37 GFLOPS | Progress: (12/20) | 8.47 s
[Task 23/25] Current/Best: 6.27/ 21.37 GFLOPS | Progress: (16/20) | 15.54 s
[Task 23/25] Current/Best: 7.86/ 21.37 GFLOPS | Progress: (20/20) | 19.78 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (4/20) | 11.80 s
[Task 24/25] Current/Best: 2.12/ 8.58 GFLOPS | Progress: (8/20) | 22.85 s
[Task 24/25] Current/Best: 4.50/ 8.58 GFLOPS | Progress: (12/20) | 34.39 s Done.
+ Done.
+
[Task 24/25] Current/Best: 6.68/ 8.77 GFLOPS | Progress: (16/20) | 39.83 s
[Task 24/25] Current/Best: 3.35/ 8.93 GFLOPS | Progress: (20/20) | 45.71 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.92 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 5.72/ 8.03 GFLOPS | Progress: (8/20) | 22.87 s
[Task 25/25] Current/Best: 5.97/ 8.03 GFLOPS | Progress: (12/20) | 34.17 s
[Task 25/25] Current/Best: 5.72/ 8.84 GFLOPS | Progress: (16/20) | 36.01 s
[Task 25/25] Current/Best: 2.90/ 9.20 GFLOPS | Progress: (20/20) | 46.70 s
@@ -654,7 +655,6 @@ model using optimized operators to speed up our computations.
.. code-block:: none
- Done.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 408.33150630998716, 'median': 408.3110431500245, 'std': 0.6670956824963112}
- unoptimized: {'mean': 475.11939588999667, 'median': 475.16727245019865, 'std': 0.4206919897508426}
+ optimized: {'mean': 408.1042289499237, 'median': 408.34412649992373, 'std': 1.0095210561851937}
+ unoptimized: {'mean': 495.14105112001744, 'median': 495.2042046500537, 'std': 1.0245270115578045}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 18.892 seconds)
+ **Total running time of the script:** ( 10 minutes 17.596 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 8e37f95e2..fa7f9f89f 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
- 1.351e-07 secs/op
+ 1.286e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 7b3cd737e..7f96aa1b0 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, 0x1ab03a50)), stage(b, placeholder(b, 0x55da6f0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0xb16a2d0)), stage(b, placeholder(b, 0x478bb10)), 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 2c578ad24..881292f35 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
=================
-**13:27.178** total execution time for **tutorial** files:
+**13:04.375** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:18.892 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:17.596 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:13.660 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.578 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.717 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:49.362 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:29.558 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.531 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.731 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.709 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.771 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.736 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.687 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.706 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.155 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.150 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 1323245dc..d543199b1 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: 0.000009
- naive: 0.000007
+ Numpy running time: 0.000008
+ naive: 0.000006
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000007
+ parallel: 0.000006
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vector: 0.000025
+ vector: 0.000024
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 9.009360001073219e-06 1.0
- naive 6.706299999999999e-06 0.7443702992444665
- parallel 7.1465999999999995e-06 0.7932416952090579
- vector 2.4632100000000004e-05 2.7340565808299107
+ numpy 7.858970002416754e-06 1.0
+ naive 5.8561000000000006e-06 0.7451485370473687
+ parallel 6.0342e-06 0.7678105398219347
+ vector 2.44416e-05 3.1100258675734644
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018007
+ Numpy running time: 0.018835
@@ -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: 3.336010
+ none: 3.294393
@@ -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: 0.298847
+ blocking: 0.314396
@@ -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: 0.336686
+ vectorization: 0.343215
@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: 0.112903
+ loop permutation: 0.114687
@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: 0.108365
+ array packing: 0.108441
@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: 0.110614
+ block caching: 0.110826
@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: 0.144166
+ parallelization: 0.144289
@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 3.3360100401000006 1.0
- blocking 0.2988468618 0.08958212301754395
- vectorization 0.33668563479999997 0.10092464673454862
- loop permutation 0.11290308460000001 0.03384374844286009
- array packing 0.1083651288 0.03248345403563343
- block caching 0.11061437470000002 0.03315768638894271
- parallelization 0.1441661326 0.04321513750470561
+ none 3.294393409 1.0
+ blocking 0.3143960812 0.09543367842501654
+ vectorization 0.3432152674 0.1041816276290395
+ loop permutation 0.1146865748 0.03481265306283279
+ array packing 0.1084409269 0.032916811514905504
+ block caching 0.1108262083 0.033640854184941095
+ parallelization 0.1442894801 0.04379849707864687
diff --git a/docs/commit_hash b/docs/commit_hash
index 125a6a019..2c07af3a1 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-dc1324635a52e9cf0a8dbf535c58e60b92fe4736
+4d84620d07630f84c60b9386484ab2d8c102a0fe
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 13c34d348..2f57b82c5 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -569,7 +569,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.258 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.708 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 e0c07f4bc..abe098d6e 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip16b432e1-3333-4845-8e3e-11d93a3c8c8a 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.zip59aa3dc7-ad17-4fe9-95fa-cc3cec82a515 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 d9e974fb9..d2bb96c30 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,13 +427,14 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 46.8MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 52.2MB/s]
- 57%|#####7 | 23.7M/41.5M [00:00<00:00, 61.9MB/s]
- 72%|#######2 | 29.9M/41.5M [00:00<00:00, 53.2MB/s]
- 85%|########4 | 35.2M/41.5M [00:00<00:00, 49.9MB/s]
- 97%|#########6| 40.2M/41.5M [00:00<00:00, 45.9MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 51.0MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 45.6MB/s]
+ 26%|##5 | 10.7M/41.5M [00:00<00:01, 30.5MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 32.2MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 41.6MB/s]
+ 64%|######4 | 26.7M/41.5M [00:00<00:00, 40.0MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 44.2MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 49.4MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 42.5MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index c48f74714..e08b7ba38 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,8 +409,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 45%|####4 | 19.9M/44.7M [00:00<00:00, 208MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 238MB/s]
+ 37%|###6 | 16.4M/44.7M [00:00<00:00, 172MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 245MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 234MB/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 91ec3e5d4..c4b947a6f 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.865 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.949 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 82a3ef824..80e1a1a3d 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>04:58.391</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:07.424</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,43 +331,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_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>01:03.865</p></td>
+<td><p>01:05.949</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:00.258</p></td>
+<td><p>01:03.708</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>00:38.973</p></td>
+<td><p>00:39.806</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>00:27.307</p></td>
+<td><p>00:27.924</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.719</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:25.505</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:25.100</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:24.741</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>00:21.611</p></td>
+<td><p>00:22.571</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>00:19.546</p></td>
+<td><p>00:20.035</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:13.536</p></td>
+<td><p>00:14.491</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>00:02.478</p></td>
+<td><p>00:02.694</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 bf67404c0..682dea4e3 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 14.9003 14.8616 15.2206 14.6544 0.1842
+ 16.5191 16.7597 16.9627 15.9348 0.4137
</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 d42023928..1d13ebb1e 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,15 +431,15 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 3%|2 | 4.42M/170M [00:00<00:03, 46.3MB/s]
- 5%|5 | 8.84M/170M [00:00<00:03, 44.6MB/s]
- 18%|#8 | 30.9M/170M [00:00<00:01, 128MB/s]
- 32%|###1 | 53.7M/170M [00:00<00:00, 171MB/s]
- 45%|####5 | 77.2M/170M [00:00<00:00, 198MB/s]
- 60%|#####9 | 101M/170M [00:00<00:00, 216MB/s]
- 74%|#######3 | 125M/170M [00:00<00:00, 227MB/s]
- 87%|########7 | 149M/170M [00:00<00:00, 234MB/s]
-100%|##########| 170M/170M [00:00<00:00, 199MB/s]
+ 3%|2 | 4.31M/170M [00:00<00:03, 45.1MB/s]
+ 5%|5 | 8.62M/170M [00:00<00:03, 45.1MB/s]
+ 18%|#8 | 31.2M/170M [00:00<00:01, 132MB/s]
+ 34%|###3 | 56.9M/170M [00:00<00:00, 187MB/s]
+ 49%|####8 | 83.2M/170M [00:00<00:00, 219MB/s]
+ 64%|######4 | 109M/170M [00:00<00:00, 237MB/s]
+ 80%|#######9 | 136M/170M [00:00<00:00, 250MB/s]
+ 95%|#########5| 162M/170M [00:00<00:00, 258MB/s]
+100%|##########| 170M/170M [00:00<00:00, 213MB/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').
@@ -534,7 +534,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 50.323 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 59.282 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 0142edd14..2f03c0033 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -475,10 +475,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 22%|##2 | 3.01M/13.6M [00:00<00:00, 31.4MB/s]
- 54%|#####4 | 7.35M/13.6M [00:00<00:00, 39.7MB/s]
- 82%|########2 | 11.1M/13.6M [00:00<00:00, 38.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 34.4MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 165MB/s]
</pre></div>
</div>
</div>
@@ -567,7 +564,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2637 90.2283 90.7898 90.1207 0.1206
+ 90.4430 90.2965 98.7597 90.0577 0.8683
</pre></div>
</div>
<div class="admonition note">
@@ -606,7 +603,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.926 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.232 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 7647fa4e1..a19acb670 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -568,7 +568,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.9349 119.9135 121.7696 119.1089 0.3718
+ 120.4985 120.4603 121.6484 119.7529 0.3493
</pre></div>
</div>
<div class="admonition note">
@@ -596,7 +596,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 59.048 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 51.939 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 413e2b5d5..183cfd52a 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.533 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.756 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 0fd107c7a..6b220e837 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,22 +436,25 @@ 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 | 6829/132723 [00:00<00:01, 68284.86KB/s]
- 12%|#1 | 15636/132723 [00:00<00:01, 79920.39KB/s]
- 18%|#8 | 24396/132723 [00:00<00:01, 83422.71KB/s]
- 25%|##5 | 33274/132723 [00:00<00:01, 85535.14KB/s]
- 32%|###1 | 41950/132723 [00:00<00:01, 85973.96KB/s]
- 38%|###8 | 50685/132723 [00:00<00:00, 86440.20KB/s]
- 45%|####4 | 59330/132723 [00:00<00:00, 86434.41KB/s]
- 51%|#####1 | 68051/132723 [00:00<00:00, 86678.23KB/s]
- 58%|#####7 | 76822/132723 [00:00<00:00, 86999.67KB/s]
- 65%|######4 | 85631/132723 [00:01<00:00, 87334.93KB/s]
- 71%|#######1 | 94401/132723 [00:01<00:00, 87442.72KB/s]
- 78%|#######7 | 103189/132723 [00:01<00:00, 87566.93KB/s]
- 84%|########4 | 111950/132723 [00:01<00:00, 87576.84KB/s]
- 91%|######### | 120708/132723 [00:01<00:00, 81909.07KB/s]
- 97%|#########7| 128973/132723 [00:01<00:00, 81810.65KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 84615.14KB/s]
+ 4%|3 | 5270/132723 [00:00<00:02, 52694.52KB/s]
+ 9%|9 | 12371/132723 [00:00<00:01, 63465.06KB/s]
+ 15%|#4 | 19324/132723 [00:00<00:01, 66222.59KB/s]
+ 20%|#9 | 26342/132723 [00:00<00:01, 67782.45KB/s]
+ 25%|##5 | 33552/132723 [00:00<00:01, 69332.75KB/s]
+ 31%|### | 40831/132723 [00:00<00:01, 70505.57KB/s]
+ 37%|###6 | 48620/132723 [00:00<00:01, 72916.34KB/s]
+ 42%|####2 | 56284/132723 [00:00<00:01, 74098.46KB/s]
+ 48%|####8 | 63878/132723 [00:00<00:00, 74671.11KB/s]
+ 54%|#####3 | 71496/132723 [00:01<00:00, 75131.55KB/s]
+ 60%|#####9 | 79221/132723 [00:01<00:00, 75777.03KB/s]
+ 65%|######5 | 86799/132723 [00:01<00:00, 72518.23KB/s]
+ 71%|#######1 | 94452/132723 [00:01<00:00, 73694.64KB/s]
+ 77%|#######6 | 101846/132723 [00:01<00:00, 70504.69KB/s]
+ 82%|########2 | 109261/132723 [00:01<00:00, 71523.61KB/s]
+ 88%|########7 | 116447/132723 [00:01<00:00, 58494.50KB/s]
+ 93%|#########2| 123306/132723 [00:01<00:00, 61008.78KB/s]
+ 99%|#########8| 130875/132723 [00:01<00:00, 64908.82KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 68716.90KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -494,7 +497,7 @@ 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 27.845 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 33.482 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 fc9a46a9f..34a3bc07c 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:38.371</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:53.218</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:50.323</p></td>
+<td><p>02:59.282</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>02:27.845</p></td>
+<td><p>02:33.482</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>01:59.048</p></td>
+<td><p>01:51.939</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>01:22.533</p></td>
+<td><p>01:26.756</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>01:07.926</p></td>
+<td><p>01:09.232</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>00:28.375</p></td>
+<td><p>00:30.174</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.316</p></td>
+<td><p>00:22.345</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 73517d459..b25bf3006 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -607,7 +607,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipe46d9a07-b21d-4c1a-b954-2eb430b5e322 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.zip4a8c9ac6-92ed-4e7a-a51b-246237330719 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 c31a62b97..3f5e741b5 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:39.409</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:41.026</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,19 +331,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:35.963</p></td>
+<td><p>00:37.849</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>00:02.160</p></td>
+<td><p>00:02.225</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.278</p></td>
+<td><p>00:00.944</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index c932364fb..d614e10b7 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6713us [6713us] (45.89%; 45.89%)
-FoldScaleAxis: 7915us [6us] (54.11%; 54.11%)
- FoldConstant: 7909us [1599us] (54.07%; 99.92%)
- InferType: 6310us [6310us] (43.14%; 79.78%)
+InferType: 6853us [6853us] (45.71%; 45.71%)
+FoldScaleAxis: 8139us [7us] (54.29%; 54.29%)
+ FoldConstant: 8132us [1638us] (54.24%; 99.91%)
+ InferType: 6494us [6494us] (43.32%; 79.86%)
</pre></div>
</div>
</div>
@@ -532,10 +532,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6207us [6207us] (44.88%; 44.88%)
-FoldScaleAxis: 7624us [4us] (55.12%; 55.12%)
- FoldConstant: 7620us [1569us] (55.09%; 99.94%)
- InferType: 6051us [6051us] (43.75%; 79.41%)
+InferType: 6409us [6409us] (44.75%; 44.75%)
+FoldScaleAxis: 7912us [6us] (55.25%; 55.25%)
+ FoldConstant: 7906us [1638us] (55.21%; 99.93%)
+ InferType: 6269us [6269us] (43.77%; 79.29%)
</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 5373fa94f..44b2bdca0 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -559,7 +559,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.184629 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.154645 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 5f13b907e..11f39e8d5 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -901,7 +901,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.604075 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.209038 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 378921b4a..baeea773a 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -456,8 +456,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.016583
-Baseline: 3.338442
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019116
+Baseline: 3.288668
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -517,7 +517,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.291724
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.302890
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -584,7 +584,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.330800
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.338207
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -645,7 +645,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115487
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116099
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -728,7 +728,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110545
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111929
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -814,7 +814,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111262
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112543
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -904,7 +904,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144914
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145124
</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 64bdc6161..e8f9d631d 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:33.877</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.221</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.564</p></td>
+<td><p>00:31.938</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>00:01.242</p></td>
+<td><p>00:01.211</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>00:01.071</p></td>
+<td><p>00:01.072</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 f1dda1262..561a43620 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:52.334</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:59.135</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -331,27 +331,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:10.868</p></td>
+<td><p>03:13.653</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:21.519</p></td>
+<td><p>01:22.581</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>00:44.791</p></td>
+<td><p>00:46.201</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>00:18.115</p></td>
+<td><p>00:19.040</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>00:08.552</p></td>
+<td><p>00:08.849</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>00:08.488</p></td>
+<td><p>00:08.812</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 f7330e9ab..04d096904 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -486,54 +486,896 @@ 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" = 112;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [36]), storage_scope = shared;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 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
- for (rc.outer.outer: int32, 0, 128) {
- for (ry.outer.outer: int32, 0, 3) {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 4) {
- if @tir.likely((threadIdx.x_1 < 9), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [36], [], scope="shared")[((threadIdx.x_1*4) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = @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) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s), 9))) && (floormod(((threadIdx.x_1*4) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s), 9) [...]
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_1: int32 = (rc.outer.outer*392)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= floormod(threadIdx.x_1, 63)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 49), 63)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 35), 63)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 21), 63)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 7), 63)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[(threadIdx.x_2*36)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 9)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 10)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 11)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 18)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 7)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 19)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 8)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 20)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 27)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 10)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 28)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 11)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 29)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 12)] = kernel[((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 13)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 14)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 15)] = kernel[((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 16)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 17)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 18)] = kernel[((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 19)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 20)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 21)] = kernel[((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9))]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 22)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 23)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4608)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 25)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4609)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 26)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4610)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4617)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 28)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4618)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 29)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4619)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4626)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 31)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4627)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 32)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4628)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 33)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4635)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 34)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4636)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 35)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4637)]
}
}
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 12) {
- let cse_var_1: int32 = (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + threadIdx.x_2)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (floordiv((cse_var_1 + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod((cse_var_1 + threadIdx.x_2), 12), 3)*9)) + (ry.outer.outer*3)) + floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 4), 9)) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 1)], 0f32, dtype=float32)
}
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 4) {
- let cse_var_2: int32 = ((rc.inner*9) + rx.outer.inner)
- {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_2]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(cse_var_2 + 1)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(cse_var_2 + 2)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(cse_var_2 + 3)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(cse_var_2 + 4)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(cse_var_2 + 5)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(cse_var_2 + 6)]*kernel.shared_1[(((threadIdx.x*12) + (rc.inner*3)) + rx.outer.inner)]))
- }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2*36)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 12)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 13)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 14)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 21)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 7)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 22)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 8)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 23)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 30)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 10)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 31)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 11)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 32)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 13)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 14)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 16)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 17)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 19)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 20)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 22)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 23)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 5)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4611)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 25)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4612)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 26)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4613)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4620)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 28)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4621)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 29)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4622)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4629)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 31)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4630)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 32)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4631)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 33)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4638)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 34)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4639)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 35)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4640)]
+ }
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((floormod(threadIdx.x_1, 63) < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 49), 63) < 54) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 35), 63) < 54) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 21), 63) < 54) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 7), 63) < 54) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) + 6)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2*36)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 15)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 16)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 17)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 24)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 7)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 25)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 8)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 26)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 33)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 10)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 34)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 11)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 35)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 13)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 14)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 4), 8)*9)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 16)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 17)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 5), 8)*9)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 19)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 20)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 6), 8)*9)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 6)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 22)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 7)]
+ }
+ if @tir.likely((threadIdx.x_2 < 11), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 23)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*3) + 1), 2)*4608)) + (rc.outer.outer*72)) + (floormod(((threadIdx.x_2*4) + 7), 8)*9)) + 8)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4614)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 25)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4615)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 26)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4616)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4623)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 28)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4624)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 29)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4625)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4632)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 31)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4633)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 32)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4634)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 33)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4641)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 34)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4642)]
+ }
+ if @tir.likely((threadIdx.x_2 < 10), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*36) + 35)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*3), 2)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 2)*36)) + 4643)]
}
}
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
}
}
- compute[(((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
+ }
}
}
</pre></div>
@@ -569,7 +1411,7 @@ 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: 0.301 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.283 ms
</pre></div>
</div>
</div>
@@ -600,18 +1442,18 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
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=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
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)
@@ -621,14 +1463,14 @@ compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -645,16 +1487,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=36)
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=32)
+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=112)
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=32)
+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=112)
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", 0)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -672,9 +1514,9 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[36];
+ __shared__ float pad_temp_shared[504];
__shared__ float kernel_shared[384];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -683,38 +1525,866 @@ extern "C" __global__ void __launch_bounds__(32) default_function_kern
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 4; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- if (((int)threadIdx.x) < 9) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) % 9))) && ((((((int)threadIdx.x) * 4) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + ax0_ax1 [...]
- }
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 12; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + ((int)threadIdx.x))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 36)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx.x)) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3))];
- }
- __syncthreads();
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_inner * 9) + rx_outer_inner)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 1)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 2)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 3)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 4)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 5)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 9) + rx_outer_inner) + 6)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_inner * 3)) + rx_outer_inner)]));
- }
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= (((int)threadIdx.x) % 63)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((9 <= ((((int)threadIdx.x) + 49) % 63)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((9 <= ((((int)threadIdx.x) + 35) % 63)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((9 <= ((((int)threadIdx.x) + 21) % 63)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = ((((2 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[(((int)threadIdx.x) * 36)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 2)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 9)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 10)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 11)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 18)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 19)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 20)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 27)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 28)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 29)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 12)] = kernel[((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 2)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 15)] = kernel[((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 16)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 17)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 2)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 18)] = kernel[((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 19)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 20)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 2)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 21)] = kernel[((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9))];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 22)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 1)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 23)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 2)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4608)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 25)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4609)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 26)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4610)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4617)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 28)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4618)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 29)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4619)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4626)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 31)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4627)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 32)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4628)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 33)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4635)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 34)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4636)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 35)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4637)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 1)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[(((int)threadIdx.x) * 36)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 5)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 12)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 13)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 14)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 21)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 22)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 23)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 30)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 31)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 32)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 5)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 16)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 17)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 5)];
}
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 19)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 20)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 5)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 3)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 22)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 4)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 23)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 5)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4611)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 25)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4612)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 26)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4613)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4620)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 28)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4621)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 29)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4622)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4629)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 31)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4630)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 32)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4631)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 33)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4638)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 34)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4639)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 35)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4640)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((((int)threadIdx.x) % 63) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((((((int)threadIdx.x) + 49) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((((((int)threadIdx.x) + 35) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((((((int)threadIdx.x) + 21) % 63) < 54) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) + 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) + 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[(((int)threadIdx.x) * 36)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 8)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 15)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 16)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 17)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 24)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 25)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 26)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 33)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 34)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 35)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 4) & 7) * 9)) + 8)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 16)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 17)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 5) & 7) * 9)) + 8)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 19)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 20)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 6) & 7) * 9)) + 8)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 6)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 22)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 7)];
+ }
+ if (((int)threadIdx.x) < 11) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 23)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 3) + 1) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 4) + 7) & 7) * 9)) + 8)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4614)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 25)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4615)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 26)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4616)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4623)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 28)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4624)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 29)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4625)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4632)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 31)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4633)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 32)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4634)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 33)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4641)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 34)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4642)];
+ }
+ if (((int)threadIdx.x) < 10) {
+ kernel_shared[((((int)threadIdx.x) * 36) + 35)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 3) >> 1) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 1) * 36)) + 4643)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ }
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
- compute[((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -750,7 +2420,7 @@ 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 10.868 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 13.653 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 afa214fd5..15863dd09 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7756 9.8054 9.8215 9.6998 0.0540
+ 9.8781 9.8723 9.9210 9.8409 0.0330
</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 a63853305..f1033d1f5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 750.1576 750.3181 750.4153 749.7394 0.2984
+ 763.8140 763.9690 766.1337 761.3394 1.9603
</pre></div>
</div>
</div>
@@ -942,7 +942,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.519 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.581 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 849442164..f63054965 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,103 +620,105 @@ 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_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [256], [])[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_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
{
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_4: int32 = (i.inner*16)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_5: int32 = ((i.inner*16) + 1)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_6: int32 = ((i.inner*16) + 2)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_7: int32 = ((i.inner*16) + 3)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_8: int32 = ((i.inner*16) + 4)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_9: int32 = ((i.inner*16) + 5)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_10: int32 = ((i.inner*16) + 6)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_11: int32 = ((i.inner*16) + 7)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_12: int32 = ((i.inner*16) + 8)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_13: int32 = ((i.inner*16) + 9)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_14: int32 = ((i.inner*16) + 10)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_15: int32 = ((i.inner*16) + 11)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_16: int32 = ((i.inner*16) + 12)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_17: int32 = ((i.inner*16) + 13)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_18: int32 = ((i.inner*16) + 14)
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_19: int32 = ((i.inner*16) + 15)
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ compute_5: Buffer(compute_4, float32, [1024], [])[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_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 32) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ {
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*512) + (i.inner*16))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
@@ -755,7 +757,7 @@ 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: 1.801 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.226 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 e3901527f..3a74afda1 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.633</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.263</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.597</p></td>
+<td><p>00:46.228</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 06d694952..b12ea6ec1 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1431,8 +1431,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 221.29/221.29 result: MeasureResult(costs=(0.0010461413241379311,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8990349769592285, timestamp=1658702222.4748678) [('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: 0.00/221.29 result: Traceback (most recent call last):
+No: 9 GFLOPS: 188.66/188.66 result: MeasureResult(costs=(0.0012271131666666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0360028743743896, timestamp=1658735941.8228946) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/188.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1555,8 +1555,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 261.75/261.75 result: MeasureResult(costs=(0.0008844501428571427,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6992511749267578, timestamp=1658702223.3393252) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+No: 11 GFLOPS: 261.65/261.65 result: MeasureResult(costs=(0.0008847866740331492,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7377474308013916, timestamp=1658735942.7469308) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1679,7 +1679,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1802,7 +1802,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1925,9 +1925,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.31/261.75 result: MeasureResult(costs=(0.04361735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.843292236328125, timestamp=1658702227.9198248) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.34/261.75 result: MeasureResult(costs=(0.06940382975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.573373317718506, timestamp=1658702229.159794) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.30/261.65 result: MeasureResult(costs=(0.0436847795,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8295247554779053, timestamp=1658735947.3164046) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/261.65 result: MeasureResult(costs=(0.06936260500000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.560149431228638, timestamp=1658735948.5655847) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1945,8 +1945,8 @@ No: 17 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.26/261.75 result: MeasureResult(costs=(0.008191259000000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3049187660217285, timestamp=1658702240.210737) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+No: 18 GFLOPS: 27.29/261.65 result: MeasureResult(costs=(0.008483467529411766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3405115604400635, timestamp=1658735959.6776476) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2069,7 +2069,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/261.75 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/261.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2232,7 +2232,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001219
+Time cost of this operator: 0.001227
</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 40ea3a0ad..3dc89730d 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 305.6 98.713 (1, 2, 10, 10, 3) 2 1 [305.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.971 0.96 (1, 6, 10, 10) 1 1 [2.971]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.012 0.327 (1, 1, 10, 10, 3) 1 1 [1.012]
-Total_time - 309.584 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.6 98.73 (1, 2, 10, 10, 3) 2 1 [309.6]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.027 0.965 (1, 6, 10, 10) 1 1 [3.027]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 0.305 (1, 1, 10, 10, 3) 1 1 [0.957]
+Total_time - 313.584 - - - - -
</pre></div>
</div>
</div>
@@ -634,10 +634,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 216.9 98.633 (1, 1, 10, 10, 6) 2 1 [216.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.171 0.987 (1, 6, 10, 10) 1 1 [2.171]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.834 0.379 (1, 3, 10, 10, 1) 1 1 [0.834]
-Total_time - 219.905 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.75 96.659 (1, 6, 10, 10, 1) 2 1 [79.75]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.791 2.17 (1, 6, 10, 10) 1 1 [1.791]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.966 1.171 (1, 1, 10, 10, 3) 1 1 [0.966]
+Total_time - 82.507 - - - - -
</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 744f12f12..6b2849317 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp2gza993c/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp10k99h1i/images/random'
</pre></div>
</div>
</div>
@@ -570,8 +570,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp2gza993c/images/target contains 8144 images
-/tmp/tmp2gza993c/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/tmp10k99h1i/images/target contains 8144 images
+/tmp/tmp10k99h1i/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -683,13 +683,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 53s - loss: 0.2120 - accuracy: 0.9264 - val_loss: 0.1517 - val_accuracy: 0.9585
+328/328 - 55s - loss: 0.2148 - accuracy: 0.9264 - val_loss: 0.1300 - val_accuracy: 0.9603
Epoch 2/3
-328/328 - 50s - loss: 0.0935 - accuracy: 0.9625 - val_loss: 0.1181 - val_accuracy: 0.9622
+328/328 - 53s - loss: 0.1003 - accuracy: 0.9622 - val_loss: 0.1086 - val_accuracy: 0.9630
Epoch 3/3
-328/328 - 50s - loss: 0.0671 - accuracy: 0.9744 - val_loss: 0.1533 - val_accuracy: 0.9543
+328/328 - 52s - loss: 0.0694 - accuracy: 0.9747 - val_loss: 0.1500 - val_accuracy: 0.9528
-<keras.callbacks.History object at 0x7fb2b22d0290>
+<keras.callbacks.History object at 0x7fc0edf6f750>
</pre></div>
</div>
</div>
@@ -951,7 +951,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 35.825 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 11.006 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 a8e46a931..b70026b8f 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:21.306</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:58.197</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,22 +331,22 @@
</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>04:35.825</p></td>
+<td><p>05:11.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:42.211</p></td>
+<td><p>00:43.830</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.268</p></td>
+<td><p>00:03.359</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
+<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>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 e62332ba2..b4eddc00c 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.479</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:42.005</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:30.031</p></td>
+<td><p>00:30.553</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.927</p></td>
+<td><p>00:09.918</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.513</p></td>
+<td><p>00:01.528</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index b031ac19b..ff708c221 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -517,7 +517,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fb2b3480320>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fc056ded440>
</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 f0392031e..146208132 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.212</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.193</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,23 +331,23 @@
</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>00:01.931</p></td>
+<td><p>00:01.959</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>00:01.037</p></td>
+<td><p>00:00.975</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>00:00.537</p></td>
+<td><p>00:00.546</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>00:00.528</p></td>
+<td><p>00:00.532</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>00:00.098</p></td>
+<td><p>00:00.101</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index db155e6c7..8e3b2e742 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -572,7 +572,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp1yhu0mby/input0.cc'\nsource_filename = \"/tmp/tmp1yhu0mby/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/tmpi56dcld2/input0.cc'\nsource_filename = \"/tmp/tmpi56dcld2/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/doxygen/array_8h__dep__incl.svg b/docs/reference/api/doxygen/array_8h__dep__incl.svg
index 8a0ba0eae..d38d8b005 100644
--- a/docs/reference/api/doxygen/array_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/array_8h__dep__incl.svg
@@ -630,7 +630,7 @@
<!-- Node95 -->
<g id="node29" class="node">
<title>Node95</title>
-<g id="a_node29"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node29"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="1225.2886,-408 1225.2886,-427 1365.2886,-427 1365.2886,-408 1225.2886,-408"/>
<text text-anchor="middle" x="1295.2886" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/bias__add_8h__incl.svg b/docs/reference/api/doxygen/bias__add_8h__incl.svg
index c92829913..9e1d29b77 100644
--- a/docs/reference/api/doxygen/bias__add_8h__incl.svg
+++ b/docs/reference/api/doxygen/bias__add_8h__incl.svg
@@ -1284,7 +1284,7 @@
<!-- Node82 -->
<g id="node39" class="node">
<title>Node82</title>
-<g id="a_node39"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node39"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="1431.1489,-537.5 1431.1489,-556.5 1533.1489,-556.5 1533.1489,-537.5 1431.1489,-537.5"/>
<text text-anchor="middle" x="1482.1489" y="-544.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/broadcast_8h__incl.svg b/docs/reference/api/doxygen/broadcast_8h__incl.svg
index b35323b14..ec7200d5c 100644
--- a/docs/reference/api/doxygen/broadcast_8h__incl.svg
+++ b/docs/reference/api/doxygen/broadcast_8h__incl.svg
@@ -1286,7 +1286,7 @@
<!-- Node81 -->
<g id="node40" class="node">
<title>Node81</title>
-<g id="a_node40"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node40"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="1981,-660.5 1981,-679.5 2083,-679.5 2083,-660.5 1981,-660.5"/>
<text text-anchor="middle" x="2032" y="-667.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/constant__utils_8h__incl.svg b/docs/reference/api/doxygen/constant__utils_8h__incl.svg
index f9237cc4b..8be483d08 100644
--- a/docs/reference/api/doxygen/constant__utils_8h__incl.svg
+++ b/docs/reference/api/doxygen/constant__utils_8h__incl.svg
@@ -88,7 +88,7 @@
<!-- Node79 -->
<g id="node38" class="node">
<title>Node79</title>
-<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="341,-660.5 341,-679.5 443,-679.5 443,-660.5 341,-660.5"/>
<text text-anchor="middle" x="392" y="-667.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/constant__utils_8h_source.html b/docs/reference/api/doxygen/constant__utils_8h_source.html
index b4816e06b..8d6a7ac14 100644
--- a/docs/reference/api/doxygen/constant__utils_8h_source.html
+++ b/docs/reference/api/doxygen/constant__utils_8h_source.html
@@ -70,7 +70,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1te_html"><div class="ttname"><a href="namespacetvm_1_1te.html">tvm::te</a></div><div class="ttdoc">Tensor expression language DSL. </div><div class="ttdef"><b>Definition:</b> extracted_task.h:33</div></div>
<div class="ttc" id="analyzer_8h_html"><div class="ttname"><a href="analyzer_8h.html">analyzer.h</a></div><div class="ttdoc">Algebra expression simplifications. </div></div>
<div class="ttc" id="classtvm_1_1arith_1_1Analyzer_html_a9b440f852f12ad0a4d8ed5ed97054425"><div class="ttname"><a href="classtvm_1_1arith_1_1Analyzer.html#a9b440f852f12ad0a4d8ed5ed97054425">tvm::arith::Analyzer::Simplify</a></div><div class="ttdeci">PrimExpr Simplify(const PrimExpr &expr, int steps=2)</div><div class="ttdoc">Simplify expr. </div></div>
-<div class="ttc" id="tir_2analysis_8h_html"><div class="ttname"><a href="tir_2analysis_8h.html">analysis.h</a></div><div class="ttdoc">Analysis utilitie and passes for TIR. </div></div>
+<div class="ttc" id="tir_2analysis_8h_html"><div class="ttname"><a href="tir_2analysis_8h.html">analysis.h</a></div><div class="ttdoc">Analysis utilities and passes for TIR. </div></div>
<div class="ttc" id="classtvm_1_1IntImmNode_html"><div class="ttname"><a href="classtvm_1_1IntImmNode.html">tvm::IntImmNode</a></div><div class="ttdoc">Constant integer literals in the program. </div><div class="ttdef"><b>Definition:</b> expr.h:489</div></div>
<div class="ttc" id="structtvm_1_1tir_1_1ExprDeepEqual_html"><div class="ttname"><a href="structtvm_1_1tir_1_1ExprDeepEqual.html">tvm::tir::ExprDeepEqual</a></div><div class="ttdoc">Compare two expressions recursively and check if they are equal to each other without var remapping...</div><div class="ttdef"><b>Definition:</b> analysis.h:54</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>
diff --git a/docs/reference/api/doxygen/detail_2broadcast_8h__incl.svg b/docs/reference/api/doxygen/detail_2broadcast_8h__incl.svg
index ac0627a78..cb24acc31 100644
--- a/docs/reference/api/doxygen/detail_2broadcast_8h__incl.svg
+++ b/docs/reference/api/doxygen/detail_2broadcast_8h__incl.svg
@@ -1407,7 +1407,7 @@
<!-- Node80 -->
<g id="node45" class="node">
<title>Node80</title>
-<g id="a_node45"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node45"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="1091,-705.5 1091,-724.5 1193,-724.5 1193,-705.5 1091,-705.5"/>
<text text-anchor="middle" x="1142" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/diagnostic_8h__dep__incl.svg b/docs/reference/api/doxygen/diagnostic_8h__dep__incl.svg
index 98a2c261c..0a6ac3a30 100644
--- a/docs/reference/api/doxygen/diagnostic_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/diagnostic_8h__dep__incl.svg
@@ -159,7 +159,7 @@
<!-- Node132 -->
<g id="node42" class="node">
<title>Node132</title>
-<g id="a_node42"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node42"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="1920.8751,-408 1920.8751,-427 2060.8751,-427 2060.8751,-408 1920.8751,-408"/>
<text text-anchor="middle" x="1990.8751" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/dir_72c2f11201cd7636dc7624de0754daa5.html b/docs/reference/api/doxygen/dir_72c2f11201cd7636dc7624de0754daa5.html
index 328c29b0e..0d0de8808 100644
--- a/docs/reference/api/doxygen/dir_72c2f11201cd7636dc7624de0754daa5.html
+++ b/docs/reference/api/doxygen/dir_72c2f11201cd7636dc7624de0754daa5.html
@@ -83,7 +83,7 @@ Directories</h2></td></tr>
<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="files"></a>
Files</h2></td></tr>
<tr class="memitem:tir_2analysis_8h"><td class="memItemLeft" align="right" valign="top">file  </td><td class="memItemRight" valign="bottom"><a class="el" href="tir_2analysis_8h.html">analysis.h</a> <a href="tir_2analysis_8h_source.html">[code]</a></td></tr>
-<tr class="memdesc:tir_2analysis_8h"><td class="mdescLeft"> </td><td class="mdescRight">Analysis utilitie and passes for TIR. <br /></td></tr>
+<tr class="memdesc:tir_2analysis_8h"><td class="mdescLeft"> </td><td class="mdescRight">Analysis utilities and passes for TIR. <br /></td></tr>
<tr class="separator:"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:buffer_8h"><td class="memItemLeft" align="right" valign="top">file  </td><td class="memItemRight" valign="bottom"><a class="el" href="buffer_8h.html">buffer.h</a> <a href="buffer_8h_source.html">[code]</a></td></tr>
<tr class="memdesc:buffer_8h"><td class="mdescLeft"> </td><td class="mdescRight">Symbolic n-dimensional array, to represent a memory buffer. <br /></td></tr>
diff --git a/docs/reference/api/doxygen/einsum_8h__incl.svg b/docs/reference/api/doxygen/einsum_8h__incl.svg
index 59f96cf95..dda5535a4 100644
--- a/docs/reference/api/doxygen/einsum_8h__incl.svg
+++ b/docs/reference/api/doxygen/einsum_8h__incl.svg
@@ -1303,7 +1303,7 @@
<!-- Node81 -->
<g id="node39" class="node">
<title>Node81</title>
-<g id="a_node39"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node39"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="650,-593.5 650,-612.5 752,-612.5 752,-593.5 650,-593.5"/>
<text text-anchor="middle" x="701" y="-600.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/error_8h__dep__incl.svg b/docs/reference/api/doxygen/error_8h__dep__incl.svg
index 9139e4797..b5686bc17 100644
--- a/docs/reference/api/doxygen/error_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/error_8h__dep__incl.svg
@@ -159,7 +159,7 @@
<!-- Node131 -->
<g id="node42" class="node">
<title>Node131</title>
-<g id="a_node42"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node42"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="2973.5,-408 2973.5,-427 3113.5,-427 3113.5,-408 2973.5,-408"/>
<text text-anchor="middle" x="3043.5" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/files.html b/docs/reference/api/doxygen/files.html
index c003a97a9..bbb26a08b 100644
--- a/docs/reference/api/doxygen/files.html
+++ b/docs/reference/api/doxygen/files.html
@@ -274,7 +274,7 @@ $(function() {
<tr id="row_0_0_13_1_2_" class="even" style="display:none;"><td class="entry"><span style="width:80px;display:inline-block;"> </span><a href="tir_2usmp_2analysis_8h_source.html"><span class="icondoc"></span></a><a class="el" href="tir_2usmp_2analysis_8h.html" target="_self">analysis.h</a></td><td class="desc">The analysis passes for TIR-based Unified Static Memory Planner </td></tr>
<tr id="row_0_0_13_1_3_" class="even" style="display:none;"><td class="entry"><span style="width:80px;display:inline-block;"> </span><a href="tir_2usmp_2transform_8h_source.html"><span class="icondoc"></span></a><a class="el" href="tir_2usmp_2transform_8h.html" target="_self">transform.h</a></td><td class="desc">The transform passes for TIR-based Unified Static Memory Planner </td></tr>
<tr id="row_0_0_13_1_4_" class="even" style="display:none;"><td class="entry"><span style="width:80px;display:inline-block;"> </span><a href="tir_2usmp_2utils_8h_source.html"><span class="icondoc"></span></a><a class="el" href="tir_2usmp_2utils_8h.html" target="_self">utils.h</a></td><td class="desc">Utilities for Unified Static Memory Planner </td></tr>
-<tr id="row_0_0_13_2_" class="even" style="display:none;"><td class="entry"><span style="width:64px;display:inline-block;"> </span><a href="tir_2analysis_8h_source.html"><span class="icondoc"></span></a><a class="el" href="tir_2analysis_8h.html" target="_self">analysis.h</a></td><td class="desc">Analysis utilitie and passes for TIR </td></tr>
+<tr id="row_0_0_13_2_" class="even" style="display:none;"><td class="entry"><span style="width:64px;display:inline-block;"> </span><a href="tir_2analysis_8h_source.html"><span class="icondoc"></span></a><a class="el" href="tir_2analysis_8h.html" target="_self">analysis.h</a></td><td class="desc">Analysis utilities and passes for TIR </td></tr>
<tr id="row_0_0_13_3_" class="even" style="display:none;"><td class="entry"><span style="width:64px;display:inline-block;"> </span><a href="buffer_8h_source.html"><span class="icondoc"></span></a><a class="el" href="buffer_8h.html" target="_self">buffer.h</a></td><td class="desc">Symbolic n-dimensional array, to represent a memory buffer </td></tr>
<tr id="row_0_0_13_4_" class="even" style="display:none;"><td class="entry"><span style="width:64px;display:inline-block;"> </span><a href="builtin_8h_source.html"><span class="icondoc"></span></a><a class="el" href="builtin_8h.html" target="_self">builtin.h</a></td><td class="desc">TIR builtin intrinsics </td></tr>
<tr id="row_0_0_13_5_" class="even" style="display:none;"><td class="entry"><span style="width:64px;display:inline-block;"> </span><a href="data__layout_8h_source.html"><span class="icondoc"></span></a><a class="el" href="data__layout_8h.html" target="_self">data_layout.h</a></td><td class="desc">Layout expression to describe the data organization of a tensor. And BijectiveLayout to mapping two data layouts between each other </td></tr>
diff --git a/docs/reference/api/doxygen/flatten_8h__incl.svg b/docs/reference/api/doxygen/flatten_8h__incl.svg
index 0aafa888d..3aac23775 100644
--- a/docs/reference/api/doxygen/flatten_8h__incl.svg
+++ b/docs/reference/api/doxygen/flatten_8h__incl.svg
@@ -1410,7 +1410,7 @@
<!-- Node80 -->
<g id="node45" class="node">
<title>Node80</title>
-<g id="a_node45"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node45"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="1793,-705.5 1793,-724.5 1895,-724.5 1895,-705.5 1793,-705.5"/>
<text text-anchor="middle" x="1844" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/functor_8h__dep__incl.svg b/docs/reference/api/doxygen/functor_8h__dep__incl.svg
index 3e04cf489..300a99282 100644
--- a/docs/reference/api/doxygen/functor_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/functor_8h__dep__incl.svg
@@ -817,7 +817,7 @@
<!-- Node94 -->
<g id="node31" class="node">
<title>Node94</title>
-<g id="a_node31"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node31"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="839.5544,-274 839.5544,-293 979.5544,-293 979.5544,-274 839.5544,-274"/>
<text text-anchor="middle" x="909.5544" y="-281" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/instrument_8h__dep__incl.svg b/docs/reference/api/doxygen/instrument_8h__dep__incl.svg
index 7b40616d5..d53149ee7 100644
--- a/docs/reference/api/doxygen/instrument_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/instrument_8h__dep__incl.svg
@@ -127,7 +127,7 @@
<!-- Node114 -->
<g id="node42" class="node">
<title>Node114</title>
-<g id="a_node42"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node42"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="2111,-408 2111,-427 2251,-427 2251,-408 2111,-408"/>
<text text-anchor="middle" x="2181" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/ir_2adt_8h__dep__incl.svg b/docs/reference/api/doxygen/ir_2adt_8h__dep__incl.svg
index fc55428c7..1680871c8 100644
--- a/docs/reference/api/doxygen/ir_2adt_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/ir_2adt_8h__dep__incl.svg
@@ -298,7 +298,7 @@
<!-- Node124 -->
<g id="node38" class="node">
<title>Node124</title>
-<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="1704.5,-408 1704.5,-427 1844.5,-427 1844.5,-408 1704.5,-408"/>
<text text-anchor="middle" x="1774.5" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/ir_2function_8h__dep__incl.svg b/docs/reference/api/doxygen/ir_2function_8h__dep__incl.svg
index 876545af2..f66b55ef7 100644
--- a/docs/reference/api/doxygen/ir_2function_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/ir_2function_8h__dep__incl.svg
@@ -313,7 +313,7 @@
<!-- Node125 -->
<g id="node32" class="node">
<title>Node125</title>
-<g id="a_node32"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node32"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="895,-408 895,-427 1035,-427 1035,-408 895,-408"/>
<text text-anchor="middle" x="965" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/ir_2module_8h__dep__incl.svg b/docs/reference/api/doxygen/ir_2module_8h__dep__incl.svg
index 7547c22dd..21b9e0da0 100644
--- a/docs/reference/api/doxygen/ir_2module_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/ir_2module_8h__dep__incl.svg
@@ -268,7 +268,7 @@
<!-- Node131 -->
<g id="node38" class="node">
<title>Node131</title>
-<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="1793,-408 1793,-427 1933,-427 1933,-408 1793,-408"/>
<text text-anchor="middle" x="1863" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/ir_2transform_8h__dep__incl.svg b/docs/reference/api/doxygen/ir_2transform_8h__dep__incl.svg
index 0452f967a..0b74db40b 100644
--- a/docs/reference/api/doxygen/ir_2transform_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/ir_2transform_8h__dep__incl.svg
@@ -112,7 +112,7 @@
<!-- Node134 -->
<g id="node41" class="node">
<title>Node134</title>
-<g id="a_node41"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node41"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="2561,-408 2561,-427 2701,-427 2701,-408 2561,-408"/>
<text text-anchor="middle" x="2631" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/map_8h__dep__incl.svg b/docs/reference/api/doxygen/map_8h__dep__incl.svg
index 49737dc95..203866431 100644
--- a/docs/reference/api/doxygen/map_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/map_8h__dep__incl.svg
@@ -274,7 +274,7 @@
<!-- Node95 -->
<g id="node8" class="node">
<title>Node95</title>
-<g id="a_node8"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node8"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="232.5,-274 232.5,-293 372.5,-293 372.5,-274 232.5,-274"/>
<text text-anchor="middle" x="302.5" y="-281" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/namespacemembers_func_v.html b/docs/reference/api/doxygen/namespacemembers_func_v.html
index cb77e2e60..8d1d7c5b2 100644
--- a/docs/reference/api/doxygen/namespacemembers_func_v.html
+++ b/docs/reference/api/doxygen/namespacemembers_func_v.html
@@ -94,6 +94,9 @@ $(function() {
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#ac51a104ab4d2c60a4f6ed0e827efab18">tvm::tir::transform</a>
, <a class="el" href="namespacetvm_1_1tir.html#a3b38edd60b6ff952cefb74842a8ae826">tvm::tir</a>
</li>
+<li>VerifyWellFormed()
+: <a class="el" href="namespacetvm_1_1tir.html#aee3d251f82ef3a0f446ea23f8980d84e">tvm::tir</a>
+</li>
<li>VisitPrimFuncs()
: <a class="el" href="namespacetvm_1_1tir.html#a1f69889b13455cd290e6b1a6453e3c1d">tvm::tir</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacemembers_v.html b/docs/reference/api/doxygen/namespacemembers_v.html
index 07186c5ba..9b4078eee 100644
--- a/docs/reference/api/doxygen/namespacemembers_v.html
+++ b/docs/reference/api/doxygen/namespacemembers_v.html
@@ -94,6 +94,9 @@ $(function() {
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#ac51a104ab4d2c60a4f6ed0e827efab18">tvm::tir::transform</a>
, <a class="el" href="namespacetvm_1_1tir.html#a3b38edd60b6ff952cefb74842a8ae826">tvm::tir</a>
</li>
+<li>VerifyWellFormed()
+: <a class="el" href="namespacetvm_1_1tir.html#aee3d251f82ef3a0f446ea23f8980d84e">tvm::tir</a>
+</li>
<li>virtual_thread
: <a class="el" href="namespacetvm_1_1tir_1_1attr.html#a464533c1560ace5e0b5071ba6902482e">tvm::tir::attr</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacetvm_1_1tir.html b/docs/reference/api/doxygen/namespacetvm_1_1tir.html
index 7e7750b77..6c0c917e1 100644
--- a/docs/reference/api/doxygen/namespacetvm_1_1tir.html
+++ b/docs/reference/api/doxygen/namespacetvm_1_1tir.html
@@ -742,6 +742,9 @@ Functions</h2></td></tr>
<tr class="memitem:abbd3ced524b506f532aa1d8ae36dadf3"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1Map.html">Map</a>< <a class="el" href="classtvm_1_1tir_1_1Buffer.html">Buffer</a>, <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a> > > </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir.html#abbd3ced524b506f53 [...]
<tr class="memdesc:abbd3ced524b506f532aa1d8ae36dadf3"><td class="mdescLeft"> </td><td class="mdescRight">Detect the lowest common ancestor(LCA) of buffer access, including both high-level access(BufferLoad, BufferStore) and low-level access(Load, Store and opaque access). The LCA may be a <a class="el" href="classtvm_1_1tir_1_1For.html" title="Managed reference to ForNode. ">For</a> loop or a <a class="el" href="classtvm_1_1tir_1_1Block.html" title="Managed reference to BlockNode. " [...]
<tr class="separator:abbd3ced524b506f532aa1d8ae36dadf3"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aee3d251f82ef3a0f446ea23f8980d84e"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir.html#aee3d251f82ef3a0f446ea23f8980d84e">VerifyWellFormed</a> (const <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html">PrimFunc</a> &func, bool assert_mode=true)</td></tr>
+<tr class="memdesc:aee3d251f82ef3a0f446ea23f8980d84e"><td class="mdescLeft"> </td><td class="mdescRight">Verify if the given TIR is well-formed. The verification includes: <a href="#aee3d251f82ef3a0f446ea23f8980d84e">More...</a><br /></td></tr>
+<tr class="separator:aee3d251f82ef3a0f446ea23f8980d84e"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a65cc94726eb40752523b952f500d00ec"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1tir_1_1Buffer.html">Buffer</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir.html#a65cc94726eb40752523b952f500d00ec">decl_buffer</a> (<a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1PrimExpr.html">PrimExpr</a> > shape, <a class="el" href="namespacetvm.ht [...]
<tr class="memdesc:a65cc94726eb40752523b952f500d00ec"><td class="mdescLeft"> </td><td class="mdescRight">Construct a new buffer given shape, and dtype. <a href="#a65cc94726eb40752523b952f500d00ec">More...</a><br /></td></tr>
<tr class="separator:a65cc94726eb40752523b952f500d00ec"><td class="memSeparator" colspan="2"> </td></tr>
@@ -3261,6 +3264,47 @@ template<typename T > </div>
<dl class="section return"><dt>Returns</dt><dd>Whether IR is in SSA form.</dd></dl>
<dl class="section note"><dt>Note</dt><dd>All passes in TIR consume and produce SSA form. </dd></dl>
+</div>
+</div>
+<a id="aee3d251f82ef3a0f446ea23f8980d84e"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#aee3d251f82ef3a0f446ea23f8980d84e">◆ </a></span>VerifyWellFormed()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">bool tvm::tir::VerifyWellFormed </td>
+ <td>(</td>
+ <td class="paramtype">const <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html">PrimFunc</a> & </td>
+ <td class="paramname"><em>func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">bool </td>
+ <td class="paramname"><em>assert_mode</em> = <code>true</code> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Verify if the given TIR is well-formed. The verification includes: </p>
+<ul>
+<li>Check if expressions not contain vars that is defined outside the block. <dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">func</td><td>The <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html" title="Managed reference to PrimFuncNode. ">PrimFunc</a> to be verified. </td></tr>
+ <tr><td class="paramname">assert_mode</td><td>The indicator if it raises an error when the function is not well-formed. </td></tr>
+ </table>
+ </dd>
+</dl>
+<dl class="section return"><dt>Returns</dt><dd>Whether it is a well-formed TIR function. </dd></dl>
+</li>
+</ul>
+
</div>
</div>
<a id="a1f69889b13455cd290e6b1a6453e3c1d"></a>
diff --git a/docs/reference/api/doxygen/nn_2bnn_8h__incl.svg b/docs/reference/api/doxygen/nn_2bnn_8h__incl.svg
index a410191d0..9148de492 100644
--- a/docs/reference/api/doxygen/nn_2bnn_8h__incl.svg
+++ b/docs/reference/api/doxygen/nn_2bnn_8h__incl.svg
@@ -1469,7 +1469,7 @@
<!-- Node80 -->
<g id="node45" class="node">
<title>Node80</title>
-<g id="a_node45"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node45"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="1307.5421,-828.5 1307.5421,-847.5 1409.5421,-847.5 1409.5421,-828.5 1307.5421,-828.5"/>
<text text-anchor="middle" x="1358.5421" y="-835.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/nn_2pooling_8h__incl.svg b/docs/reference/api/doxygen/nn_2pooling_8h__incl.svg
index f39c8547f..73c81b917 100644
--- a/docs/reference/api/doxygen/nn_2pooling_8h__incl.svg
+++ b/docs/reference/api/doxygen/nn_2pooling_8h__incl.svg
@@ -1303,7 +1303,7 @@
<!-- Node82 -->
<g id="node39" class="node">
<title>Node82</title>
-<g id="a_node39"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node39"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="2064,-593.5 2064,-612.5 2166,-612.5 2166,-593.5 2064,-593.5"/>
<text text-anchor="middle" x="2115" y="-600.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/nn_2softmax_8h__incl.svg b/docs/reference/api/doxygen/nn_2softmax_8h__incl.svg
index da36a5d75..064999a3c 100644
--- a/docs/reference/api/doxygen/nn_2softmax_8h__incl.svg
+++ b/docs/reference/api/doxygen/nn_2softmax_8h__incl.svg
@@ -1336,7 +1336,7 @@
<!-- Node83 -->
<g id="node40" class="node">
<title>Node83</title>
-<g id="a_node40"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node40"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="1065,-537.5 1065,-556.5 1167,-556.5 1167,-537.5 1065,-537.5"/>
<text text-anchor="middle" x="1116" y="-544.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/optional_8h__dep__incl.svg b/docs/reference/api/doxygen/optional_8h__dep__incl.svg
index cb1d6936b..af87f1a5f 100644
--- a/docs/reference/api/doxygen/optional_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/optional_8h__dep__incl.svg
@@ -582,7 +582,7 @@
<!-- Node99 -->
<g id="node21" class="node">
<title>Node99</title>
-<g id="a_node21"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node21"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="28,-274 28,-293 168,-293 168,-274 28,-274"/>
<text text-anchor="middle" x="98" y="-281" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/reduction_8h__incl.svg b/docs/reference/api/doxygen/reduction_8h__incl.svg
index 7c0c33474..98955af15 100644
--- a/docs/reference/api/doxygen/reduction_8h__incl.svg
+++ b/docs/reference/api/doxygen/reduction_8h__incl.svg
@@ -1275,7 +1275,7 @@
<!-- Node82 -->
<g id="node38" class="node">
<title>Node82</title>
-<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="786,-481.5 786,-500.5 888,-500.5 888,-481.5 786,-481.5"/>
<text text-anchor="middle" x="837" y="-488.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/reorg_8h__incl.svg b/docs/reference/api/doxygen/reorg_8h__incl.svg
index aeaeb4db7..dd4a1951d 100644
--- a/docs/reference/api/doxygen/reorg_8h__incl.svg
+++ b/docs/reference/api/doxygen/reorg_8h__incl.svg
@@ -1152,7 +1152,7 @@
<!-- Node80 -->
<g id="node36" class="node">
<title>Node80</title>
-<g id="a_node36"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node36"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="2381,-481.5 2381,-500.5 2483,-500.5 2483,-481.5 2381,-481.5"/>
<text text-anchor="middle" x="2432" y="-488.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/runtime_2container_2adt_8h__dep__incl.svg b/docs/reference/api/doxygen/runtime_2container_2adt_8h__dep__incl.svg
index bac808469..cfde5ef90 100644
--- a/docs/reference/api/doxygen/runtime_2container_2adt_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/runtime_2container_2adt_8h__dep__incl.svg
@@ -330,7 +330,7 @@
<!-- Node94 -->
<g id="node37" class="node">
<title>Node94</title>
-<g id="a_node37"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node37"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="1687.5252,-408 1687.5252,-427 1827.5252,-427 1827.5252,-408 1687.5252,-408"/>
<text text-anchor="middle" x="1757.5252" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/search/all_14.js b/docs/reference/api/doxygen/search/all_14.js
index 649cb8937..39aaf7ad5 100644
--- a/docs/reference/api/doxygen/search/all_14.js
+++ b/docs/reference/api/doxygen/search/all_14.js
@@ -166,7 +166,7 @@ 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']]],
diff --git a/docs/reference/api/doxygen/search/all_17.js b/docs/reference/api/doxygen/search/all_17.js
index 9d59a5184..18094dbfc 100644
--- a/docs/reference/api/doxygen/search/all_17.js
+++ b/docs/reference/api/doxygen/search/all_17.js
@@ -42,6 +42,7 @@ var searchData=
['verifygpucode',['VerifyGPUCode',['../classtvm_1_1meta__schedule_1_1Postproc.html#a7106b1742068c45966d6be5f4b8394aa',1,'tvm::meta_schedule::Postproc::VerifyGPUCode()'],['../namespacetvm_1_1tir.html#a53dfcb6ef7e178a83fda0bbb5dddcb39',1,'tvm::tir::VerifyGPUCode()'],['../namespacetvm_1_1tir_1_1transform.html#a70a059926c2ea81dcf437eff35f05e3e',1,'tvm::tir::transform::VerifyGPUCode()']]],
['verifymemory',['VerifyMemory',['../namespacetvm_1_1tir.html#ac69bcf127843e5e671379e44ab47ca27',1,'tvm::tir::VerifyMemory()'],['../namespacetvm_1_1tir_1_1transform.html#a32d0b0ed966cf019d5e607bc90f284af',1,'tvm::tir::transform::VerifyMemory()']]],
['verifyssa',['VerifySSA',['../namespacetvm_1_1tir.html#a3b38edd60b6ff952cefb74842a8ae826',1,'tvm::tir::VerifySSA()'],['../namespacetvm_1_1tir_1_1transform.html#ac51a104ab4d2c60a4f6ed0e827efab18',1,'tvm::tir::transform::VerifySSA()']]],
+ ['verifywellformed',['VerifyWellFormed',['../namespacetvm_1_1tir.html#aee3d251f82ef3a0f446ea23f8980d84e',1,'tvm::tir']]],
['version',['version',['../structTVMMetadata.html#ade3312efd4c0e5beaf390959621b2f52',1,'TVMMetadata::version()'],['../classtvm_1_1runtime_1_1metadata_1_1MetadataNode.html#a894ca3986db9874b364ea83982e54f21',1,'tvm::runtime::metadata::MetadataNode::version()']]],
['vid',['vid',['../classtvm_1_1relay_1_1VarNode.html#af191a8eedf3575d626771c9c820ddb63',1,'tvm::relay::VarNode']]],
['virtual_5fdevice',['virtual_device',['../structtvm_1_1relay_1_1AllocStorageAttrs.html#afdf3a337a2f431b6243a646a3d6ef158',1,'tvm::relay::AllocStorageAttrs::virtual_device()'],['../structtvm_1_1relay_1_1OnDeviceAttrs.html#ad65024d20dad91bc92ce3c6c5ed507d2',1,'tvm::relay::OnDeviceAttrs::virtual_device()'],['../classtvm_1_1RelayExprNode.html#ac4e639dd9f33f304800851364f471eb1',1,'tvm::RelayExprNode::virtual_device()']]],
diff --git a/docs/reference/api/doxygen/search/functions_16.js b/docs/reference/api/doxygen/search/functions_16.js
index afe90b11a..a63db1a8a 100644
--- a/docs/reference/api/doxygen/search/functions_16.js
+++ b/docs/reference/api/doxygen/search/functions_16.js
@@ -16,6 +16,7 @@ var searchData=
['verifygpucode',['VerifyGPUCode',['../classtvm_1_1meta__schedule_1_1Postproc.html#a7106b1742068c45966d6be5f4b8394aa',1,'tvm::meta_schedule::Postproc::VerifyGPUCode()'],['../namespacetvm_1_1tir.html#a53dfcb6ef7e178a83fda0bbb5dddcb39',1,'tvm::tir::VerifyGPUCode()'],['../namespacetvm_1_1tir_1_1transform.html#a70a059926c2ea81dcf437eff35f05e3e',1,'tvm::tir::transform::VerifyGPUCode()']]],
['verifymemory',['VerifyMemory',['../namespacetvm_1_1tir.html#ac69bcf127843e5e671379e44ab47ca27',1,'tvm::tir::VerifyMemory()'],['../namespacetvm_1_1tir_1_1transform.html#a32d0b0ed966cf019d5e607bc90f284af',1,'tvm::tir::transform::VerifyMemory()']]],
['verifyssa',['VerifySSA',['../namespacetvm_1_1tir.html#a3b38edd60b6ff952cefb74842a8ae826',1,'tvm::tir::VerifySSA()'],['../namespacetvm_1_1tir_1_1transform.html#ac51a104ab4d2c60a4f6ed0e827efab18',1,'tvm::tir::transform::VerifySSA()']]],
+ ['verifywellformed',['VerifyWellFormed',['../namespacetvm_1_1tir.html#aee3d251f82ef3a0f446ea23f8980d84e',1,'tvm::tir']]],
['version',['version',['../classtvm_1_1runtime_1_1metadata_1_1MetadataNode.html#a894ca3986db9874b364ea83982e54f21',1,'tvm::runtime::metadata::MetadataNode']]],
['virtual_5fdevice',['virtual_device',['../classtvm_1_1RelayExprNode.html#ac4e639dd9f33f304800851364f471eb1',1,'tvm::RelayExprNode']]],
['virtualdevice',['VirtualDevice',['../classtvm_1_1VirtualDevice.html#a3fc9e14cd829c1f44b3b2da4f6c1b47f',1,'tvm::VirtualDevice']]],
diff --git a/docs/reference/api/doxygen/source__map_8h__dep__incl.svg b/docs/reference/api/doxygen/source__map_8h__dep__incl.svg
index c47c91259..3d7547ecc 100644
--- a/docs/reference/api/doxygen/source__map_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/source__map_8h__dep__incl.svg
@@ -190,7 +190,7 @@
<!-- Node122 -->
<g id="node37" class="node">
<title>Node122</title>
-<g id="a_node37"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node37"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="1887,-408 1887,-427 2027,-427 2027,-408 1887,-408"/>
<text text-anchor="middle" x="1957" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/stmt_8h__dep__incl.svg b/docs/reference/api/doxygen/stmt_8h__dep__incl.svg
index 249ea10d3..caa76f604 100644
--- a/docs/reference/api/doxygen/stmt_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/stmt_8h__dep__incl.svg
@@ -33,7 +33,7 @@
<!-- Node118 -->
<g id="node30" class="node">
<title>Node118</title>
-<g id="a_node30"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node30"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="887.5,-587 887.5,-606 1027.5,-606 1027.5,-587 887.5,-587"/>
<text text-anchor="middle" x="957.5" y="-594" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/strided__slice_8h__incl.svg b/docs/reference/api/doxygen/strided__slice_8h__incl.svg
index ec3ce9379..ae6daf692 100644
--- a/docs/reference/api/doxygen/strided__slice_8h__incl.svg
+++ b/docs/reference/api/doxygen/strided__slice_8h__incl.svg
@@ -1178,7 +1178,7 @@
<!-- Node80 -->
<g id="node49" class="node">
<title>Node80</title>
-<g id="a_node49"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node49"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="1164,-873.5 1164,-892.5 1266,-892.5 1266,-873.5 1164,-873.5"/>
<text text-anchor="middle" x="1215" y="-880.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/tir_2analysis_8h.html b/docs/reference/api/doxygen/tir_2analysis_8h.html
index 2515093d5..4da073dd3 100644
--- a/docs/reference/api/doxygen/tir_2analysis_8h.html
+++ b/docs/reference/api/doxygen/tir_2analysis_8h.html
@@ -71,7 +71,7 @@ $(function() {
</div><!--header-->
<div class="contents">
-<p>Analysis utilitie and passes for TIR.
+<p>Analysis utilities and passes for TIR.
<a href="#details">More...</a></p>
<div class="textblock"><code>#include <<a class="el" href="ir_2module_8h_source.html">tvm/ir/module.h</a>></code><br />
<code>#include <<a class="el" href="ir_2transform_8h_source.html">tvm/ir/transform.h</a>></code><br />
@@ -162,6 +162,9 @@ Functions</h2></td></tr>
<tr class="memitem:abbd3ced524b506f532aa1d8ae36dadf3"><td class="memItemLeft" align="right" valign="top">Map< Buffer, Optional< Stmt > > </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir.html#abbd3ced524b506f532aa1d8ae36dadf3">tvm::tir::DetectBufferAccessLCA</a> (const PrimFunc &func)</td></tr>
<tr class="memdesc:abbd3ced524b506f532aa1d8ae36dadf3"><td class="mdescLeft"> </td><td class="mdescRight">Detect the lowest common ancestor(LCA) of buffer access, including both high-level access(BufferLoad, BufferStore) and low-level access(Load, Store and opaque access). The LCA may be a <a class="el" href="classtvm_1_1tir_1_1For.html" title="Managed reference to ForNode. ">For</a> loop or a <a class="el" href="classtvm_1_1tir_1_1Block.html" title="Managed reference to BlockNode. " [...]
<tr class="separator:abbd3ced524b506f532aa1d8ae36dadf3"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aee3d251f82ef3a0f446ea23f8980d84e"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir.html#aee3d251f82ef3a0f446ea23f8980d84e">tvm::tir::VerifyWellFormed</a> (const PrimFunc &func, bool assert_mode=true)</td></tr>
+<tr class="memdesc:aee3d251f82ef3a0f446ea23f8980d84e"><td class="mdescLeft"> </td><td class="mdescRight">Verify if the given TIR is well-formed. The verification includes: <a href="namespacetvm_1_1tir.html#aee3d251f82ef3a0f446ea23f8980d84e">More...</a><br /></td></tr>
+<tr class="separator:aee3d251f82ef3a0f446ea23f8980d84e"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:ac51a104ab4d2c60a4f6ed0e827efab18"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#ac51a104ab4d2c60a4f6ed0e827efab18">tvm::tir::transform::VerifySSA</a> ()</td></tr>
<tr class="memdesc:ac51a104ab4d2c60a4f6ed0e827efab18"><td class="mdescLeft"> </td><td class="mdescRight">Pass variant of VerifySSA. <a href="namespacetvm_1_1tir_1_1transform.html#ac51a104ab4d2c60a4f6ed0e827efab18">More...</a><br /></td></tr>
<tr class="separator:ac51a104ab4d2c60a4f6ed0e827efab18"><td class="memSeparator" colspan="2"> </td></tr>
@@ -173,7 +176,7 @@ Functions</h2></td></tr>
<tr class="separator:a70a059926c2ea81dcf437eff35f05e3e"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
-<div class="textblock"><p>Analysis utilitie and passes for TIR. </p>
+<div class="textblock"><p>Analysis utilities and passes for TIR. </p>
</div></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/tir_2analysis_8h_source.html b/docs/reference/api/doxygen/tir_2analysis_8h_source.html
index 07142e2e4..d48d587b1 100644
--- a/docs/reference/api/doxygen/tir_2analysis_8h_source.html
+++ b/docs/reference/api/doxygen/tir_2analysis_8h_source.html
@@ -66,11 +66,12 @@ $(function() {
<div class="title">analysis.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="tir_2analysis_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 mo [...]
+<a href="tir_2analysis_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 mo [...]
<div class="ttc" id="namespacetvm_1_1tir_html_abbd3ced524b506f532aa1d8ae36dadf3"><div class="ttname"><a href="namespacetvm_1_1tir.html#abbd3ced524b506f532aa1d8ae36dadf3">tvm::tir::DetectBufferAccessLCA</a></div><div class="ttdeci">Map< Buffer, Optional< Stmt > > DetectBufferAccessLCA(const PrimFunc &func)</div><div class="ttdoc">Detect the lowest common ancestor(LCA) of buffer access, including both high-level access(BufferLoad...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_ad22fd3c129c23e8e724a4772084f802c"><div class="ttname"><a href="namespacetvm_1_1tir.html#ad22fd3c129c23e8e724a4772084f802c">tvm::tir::GetBlockReadWriteRegion</a></div><div class="ttdeci">Array< Array< BufferRegion > > GetBlockReadWriteRegion(const Block &block, const Map< Var, Buffer > &buffer_var_map)</div><div class="ttdoc">Auto detect the block read/write region according to its body stmt. An opaque access will be [...]
<div class="ttc" id="ir_2module_8h_html"><div class="ttname"><a href="ir_2module_8h.html">module.h</a></div><div class="ttdoc">IRModule that holds the functions and type definitions. </div></div>
<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_html_aee3d251f82ef3a0f446ea23f8980d84e"><div class="ttname"><a href="namespacetvm_1_1tir.html#aee3d251f82ef3a0f446ea23f8980d84e">tvm::tir::VerifyWellFormed</a></div><div class="ttdeci">bool VerifyWellFormed(const PrimFunc &func, bool assert_mode=true)</div><div class="ttdoc">Verify if the given TIR is well-formed. The verification includes: </div></div>
<div class="ttc" id="tir_2op__attr__types_8h_html"><div class="ttname"><a href="tir_2op__attr__types_8h.html">op_attr_types.h</a></div><div class="ttdoc">Attribute types in the Op registry for TIR ops. </div></div>
<div class="ttc" id="classtvm_1_1tir_1_1VarNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1VarNode.html">tvm::tir::VarNode</a></div><div class="ttdoc">A variable node in the IR. </div><div class="ttdef"><b>Definition:</b> var.h:47</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1PrimFuncNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1PrimFuncNode.html">tvm::tir::PrimFuncNode</a></div><div class="ttdoc">Primitive functions that contains TIR statements. </div><div class="ttdef"><b>Definition:</b> function.h:46</div></div>
diff --git a/docs/reference/api/doxygen/tir_2expr_8h__dep__incl.svg b/docs/reference/api/doxygen/tir_2expr_8h__dep__incl.svg
index 05aacac53..36398d292 100644
--- a/docs/reference/api/doxygen/tir_2expr_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/tir_2expr_8h__dep__incl.svg
@@ -249,7 +249,7 @@
<!-- Node146 -->
<g id="node41" class="node">
<title>Node146</title>
-<g id="a_node41"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node41"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="52,-330 52,-349 192,-349 192,-330 52,-330"/>
<text text-anchor="middle" x="122" y="-337" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/tir_2function_8h__dep__incl.svg b/docs/reference/api/doxygen/tir_2function_8h__dep__incl.svg
index 4815e802b..653d83355 100644
--- a/docs/reference/api/doxygen/tir_2function_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/tir_2function_8h__dep__incl.svg
@@ -82,7 +82,7 @@
<!-- Node84 -->
<g id="node30" class="node">
<title>Node84</title>
-<g id="a_node30"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node30"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="1589,-475 1589,-494 1729,-494 1729,-475 1589,-475"/>
<text text-anchor="middle" x="1659" y="-482" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/tir_2op__attr__types_8h__dep__incl.svg b/docs/reference/api/doxygen/tir_2op__attr__types_8h__dep__incl.svg
index 74616d480..309f1471d 100644
--- a/docs/reference/api/doxygen/tir_2op__attr__types_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/tir_2op__attr__types_8h__dep__incl.svg
@@ -19,7 +19,7 @@
<!-- Node49 -->
<g id="node2" class="node">
<title>Node49</title>
-<g id="a_node2"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node2"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="337.4229,-458.5 337.4229,-477.5 477.4229,-477.5 477.4229,-458.5 337.4229,-458.5"/>
<text text-anchor="middle" x="407.4229" y="-465.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/topi_2nn_8h__incl.svg b/docs/reference/api/doxygen/topi_2nn_8h__incl.svg
index 6267d9f70..14a5034e4 100644
--- a/docs/reference/api/doxygen/topi_2nn_8h__incl.svg
+++ b/docs/reference/api/doxygen/topi_2nn_8h__incl.svg
@@ -1244,7 +1244,7 @@
<!-- Node80 -->
<g id="node38" class="node">
<title>Node80</title>
-<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node38"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="2118.0577,-593.5 2118.0577,-612.5 2220.0577,-612.5 2220.0577,-593.5 2118.0577,-593.5"/>
<text text-anchor="middle" x="2169.0577" y="-600.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/topi_2transform_8h__incl.svg b/docs/reference/api/doxygen/topi_2transform_8h__incl.svg
index 09449972b..71c5dee63 100644
--- a/docs/reference/api/doxygen/topi_2transform_8h__incl.svg
+++ b/docs/reference/api/doxygen/topi_2transform_8h__incl.svg
@@ -1478,7 +1478,7 @@
<!-- Node83 -->
<g id="node42" class="node">
<title>Node83</title>
-<g id="a_node42"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node42"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#ff0000" points="2112,-593.5 2112,-612.5 2214,-612.5 2214,-593.5 2112,-593.5"/>
<text text-anchor="middle" x="2163" y="-600.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/var_8h__dep__incl.svg b/docs/reference/api/doxygen/var_8h__dep__incl.svg
index 04d26a8ed..65a773151 100644
--- a/docs/reference/api/doxygen/var_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/var_8h__dep__incl.svg
@@ -798,7 +798,7 @@
<!-- Node146 -->
<g id="node39" class="node">
<title>Node146</title>
-<g id="a_node39"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node39"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="1502.8063,-453 1502.8063,-472 1642.8063,-472 1642.8063,-453 1502.8063,-453"/>
<text text-anchor="middle" x="1572.8063" y="-460" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/doxygen/with_8h__dep__incl.svg b/docs/reference/api/doxygen/with_8h__dep__incl.svg
index 611a24d06..f681b5777 100644
--- a/docs/reference/api/doxygen/with_8h__dep__incl.svg
+++ b/docs/reference/api/doxygen/with_8h__dep__incl.svg
@@ -684,7 +684,7 @@
<!-- Node106 -->
<g id="node49" class="node">
<title>Node106</title>
-<g id="a_node49"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilitie and passes for TIR. ">
+<g id="a_node49"><a xlink:href="tir_2analysis_8h.html" target="_top" xlink:title="Analysis utilities and passes for TIR. ">
<polygon fill="#ffffff" stroke="#000000" points="2856.7647,-408 2856.7647,-427 2996.7647,-427 2996.7647,-408 2856.7647,-408"/>
<text text-anchor="middle" x="2926.7647" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">include/tvm/tir/analysis.h</text>
</a>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index accc8b64a..03a967422 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1597,7 +1597,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1881,7 +1881,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index e3f0ab935..fe62dccf3 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -7957,6 +7957,9 @@ Will lower to scalar loop when it is turned off.</p>
<tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">verify_ssa</span></code>(func)</p></td>
<td><p>Verify if the func is in SSA form.</p></td>
</tr>
+<tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">verify_well_formed</span></code>(func[, assert_mode])</p></td>
+<td><p>Verify if the given TIR is well-formed. The verification includes:</p></td>
+</tr>
</tbody>
</table>
<dl class="py class">
@@ -8840,6 +8843,31 @@ denotes ‘no constraint’.</p>
</dl>
</dd></dl>
+<dl class="py function">
+<dt class="sig sig-object py">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.analysis.</span></span><span class="sig-name descname"><span class="pre">verify_well_formed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference internal" href="#tvm.tir.PrimFunc" title="tvm.tir.function.PrimFunc"><span class="pre">tvm.tir.function.PrimFunc</span></a></span [...]
+<dd><dl class="simple">
+<dt>Verify if the given TIR is well-formed. The verification includes:</dt><dd><ul class="simple">
+<li><p>Check if expressions not contain vars that is defined outside the block.</p></li>
+</ul>
+</dd>
+</dl>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>func</strong> (<a class="reference internal" href="#tvm.tir.PrimFunc" title="tvm.tir.PrimFunc"><em>tvm.tir.PrimFunc</em></a>) – The function to be verified.</p></li>
+<li><p><strong>assert_mode</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a>) – The indicator if it raises an error when the function is not well-formed.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>result</strong> – Whether it is a well-formed TIR function.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)">bool</a></p>
+</dd>
+</dl>
+</dd></dl>
+
</div>
<div class="section" id="module-tvm.tir.stmt_functor">
<span id="tvm-tir-stmt-functor"></span><h1>tvm.tir.stmt_functor<a class="headerlink" href="#module-tvm.tir.stmt_functor" title="Permalink to this headline">¶</a></h1>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index eaac2de33..72384c8b0 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/dc1324635/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 b2f624746..3a96c4f6f 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/dc1324635/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 b7852a711..1bf806caf 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/dc1324635/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 8444b5c2c..edab291f2 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/dc1324635/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 19c84fa34..46d2c1d45 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/dc1324635/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 bccf1c669..ed5aa0f2c 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/dc1324635/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 570d07ab5..3c0261422 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/dc1324635/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 be480956e..b842f6000 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/dc1324635/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 f991f9775..4d6d89278 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/dc1324635/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 d58534f83..656143ae6 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/dc1324635/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 dac43cc9e..42ee27367 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/dc1324635/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 f7581efc0..1d5c76c9c 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/dc1324635/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 53c0209f8..471074f9c 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/dc1324635/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 31a88d971..4ff90493f 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/dc1324635/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 bd4cf8ba6..6ab20ff1e 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/dc1324635/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 e74375028..9a67616c4 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/dc1324635/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 99d8c6fe8..c422a4191 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/dc1324635/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 995ccd818..acbf24260 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/dc1324635/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 3c9ca159c..937681281 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/dc1324635/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 01815c8ab..c0430cd27 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/dc1324635/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 557518756..a056335c9 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/dc1324635/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 4d6104c40..3c945f8f7 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/dc1324635/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 006a7d91b..f1d21f7bc 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/dc1324635/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 9dbcd6cbb..c418dd881 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/dc1324635/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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/dc1324635/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d84620d0/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 450169660..12cd97d5e 100644
... 781 lines suppressed ...