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 2022/09/01 18:57:59 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@e814f798edc5bf6977a4f4f74ec8d1d7e363c608)
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 2d2fcdac5 deploying docs (apache/tvm@e814f798edc5bf6977a4f4f74ec8d1d7e363c608)
2d2fcdac5 is described below
commit 2d2fcdac5cc9b0684fafbbc0ba71b8f274c4c6a2
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Sep 1 18:57:52 2022 +0000
deploying docs (apache/tvm@e814f798edc5bf6977a4f4f74ec8d1d7e363c608)
---
.../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 | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1209 ++++++++++++++------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 40 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 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 | 58 +-
.../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 | 16 +-
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 | 21 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../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 | 39 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1209 ++++++++++++++------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 40 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 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 +-
.../doxygen/classtvm_1_1runtime_1_1ModuleNode.html | 2 +-
...vm_1_1runtime_1_1ModuleNode__inherit__graph.svg | 218 ++--
...tvm_1_1runtime_1_1vm_1_1Executable-members.html | 42 +-
.../classtvm_1_1runtime_1_1vm_1_1Executable.html | 47 +
...1_1runtime_1_1vm_1_1Executable__coll__graph.svg | 54 +-
...runtime_1_1vm_1_1Executable__inherit__graph.svg | 54 +-
.../api/doxygen/executable_8h_source.html | 21 +-
docs/reference/api/doxygen/functions_func_g.html | 7 +-
docs/reference/api/doxygen/functions_func_l.html | 5 +-
docs/reference/api/doxygen/functions_func_t.html | 6 +-
docs/reference/api/doxygen/functions_func_u.html | 2 +-
docs/reference/api/doxygen/functions_g.html | 7 +-
docs/reference/api/doxygen/functions_l.html | 7 +-
docs/reference/api/doxygen/functions_m.html | 2 +-
docs/reference/api/doxygen/functions_s.html | 4 +-
docs/reference/api/doxygen/functions_t.html | 2 +-
docs/reference/api/doxygen/functions_u.html | 2 +-
docs/reference/api/doxygen/search/all_11.js | 6 +-
docs/reference/api/doxygen/search/all_14.js | 6 +-
docs/reference/api/doxygen/search/all_15.js | 2 +-
docs/reference/api/doxygen/search/all_16.js | 4 +-
docs/reference/api/doxygen/search/all_18.js | 2 +-
docs/reference/api/doxygen/search/all_8.js | 1 +
docs/reference/api/doxygen/search/all_d.js | 1 +
docs/reference/api/doxygen/search/all_e.js | 4 +-
docs/reference/api/doxygen/search/functions_10.js | 4 +-
docs/reference/api/doxygen/search/functions_13.js | 4 +-
docs/reference/api/doxygen/search/functions_14.js | 2 +-
docs/reference/api/doxygen/search/functions_15.js | 2 +-
docs/reference/api/doxygen/search/functions_7.js | 1 +
docs/reference/api/doxygen/search/functions_c.js | 1 +
docs/reference/api/doxygen/search/functions_d.js | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 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 | 32 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
153 files changed, 2813 insertions(+), 1824 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 1370359b6..be420daad 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 5.914 seconds)
+ **Total running time of the script:** ( 1 minutes 5.087 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 4dd6811cf..7ffe9b5c0 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.zip8841a18d-8118-4067-83d4-f7df722b6563 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2f230d7a-e57a-473a-8ce9-6ee9b2886e82 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 051231672..51deb57b8 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 43.3MB/s]
25%|##5 | 10.5M/41.5M [00:00<00:00, 35.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 35.6MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 40.1MB/s]
63%|######3 | 26.2M/41.5M [00:00<00:00, 38.5MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 36.3MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 30.9MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 34.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 43.1MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 39.7MB/s]
44%|####3 | 18.1M/41.5M [00:00<00:00, 31.1MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 29.0MB/s]
60%|###### | 25.1M/41.5M [00:00<00:00, 25.2MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 29.2MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 33.7MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 32.6MB/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 f8660a51c..2404bfa9c 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]
41%|####1 | 18.5M/44.7M [00:00<00:00, 194MB/s]
98%|#########8| 44.0M/44.7M [00:00<00:00, 237MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 231MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
44%|####3 | 19.6M/44.7M [00:00<00:00, 206MB/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 e892e9aad..160605e59 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 6.252 seconds)
+ **Total running time of the script:** ( 1 minutes 2.811 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 083420d55..efac81b08 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:17.954** total execution time for **how_to_compile_models** files:
+**05:08.244** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:06.252 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:05.087 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:05.914 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.811 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:41.435 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.585 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:29.830 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:29.057 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.748 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.392 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.729 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.901 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.778 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.296 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.474 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.663 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.313 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.043 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.482 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.409 | 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 f70579570..e63dd625f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2969 16.2793 16.7325 15.9991 0.1869
+ 16.2342 16.0242 16.9421 15.7300 0.4926
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 b67da73f1..e06fafd02 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|1 | 3.30M/170M [00:00<00:05, 34.5MB/s]
4%|3 | 6.59M/170M [00:00<00:05, 32.7MB/s]
13%|#2 | 21.9M/170M [00:00<00:01, 89.5MB/s]
23%|##3 | 39.4M/170M [00:00<00:01, 123MB/s]
33%|###2 | 55.8M/170M [00:00<00:00, 140MB/s]
45%|####4 | 76.2M/170M [00:00<00:00, 165MB/s]
58%|#####8 | 99.3M/170M [00:00<00:00, 190MB/s]
72%|#######2 | 123M/170M [00:00<00:00, 205MB/s]
84%|########3 | 142M/170M [00:00<00:00, 201MB/s]
95%|#########5| 162M/170M [00:01<00:00, 203MB/s]
100%|##########| 170M/170M [00:01<00:00, 169MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
10%|# | 17.4M/170M [00:00<00:00, 182MB/s]
25%|##4 | 42.0M/170M [00:00<00:00, 227MB/s]
40%|###9 | 67.6M/170M [00:00<00:00, 246MB/s]
55%|#####4 | 93.2M/170M [00:00<00:00, 255MB/s]
70%|####### | 120M/170M [00:00<00:00, 262MB/s]
85%|########5 | 145M/170M [00:00<00:00, 254MB/s]
99%|#########9| 169M/170M [00:00<00:00, 252MB/s]
100%|##########| 170M/170M [00:00<00:00, 248MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 1.461 seconds)
+ **Total running time of the script:** ( 2 minutes 57.369 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 c0dd10153..8b16715f6 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]
100%|##########| 13.6M/13.6M [00:00<00:00, 181MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 202MB/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)
- 90.3182 90.2006 93.1299 90.0170 0.3694
+ 90.1958 90.0433 95.9251 89.9258 0.6247
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.732 seconds)
+ **Total running time of the script:** ( 1 minutes 9.184 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 7eb400ab4..6b22f84b4 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)
- 120.3434 120.2225 122.8440 119.3696 0.4921
+ 120.3033 120.2422 123.1208 119.4754 0.4228
@@ -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 58.651 seconds)
+ **Total running time of the script:** ( 1 minutes 58.694 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 72811ca36..95460653a 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 41.319 seconds)
+ **Total running time of the script:** ( 1 minutes 35.506 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 29c8cded8..fa05a719b 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%|4 | 6435/132723 [00:00<00:01, 64342.39KB/s]
11%|#1 | 14873/132723 [00:00<00:01, 76121.11KB/s]
17%|#7 | 23210/132723 [00:00<00:01, 79425.86KB/s]
24%|##3 | 31697/132723 [00:00<00:01, 81566.85KB/s]
30%|### | 39854/132723 [00:00<00:01, 79727.16KB/s]
36%|###6 | 48402/132723 [00:00<00:01, 81643.15KB/s]
43%|####2 | 56574/132723 [00:00<00:01, 70251.76KB/s]
49%|####9 | 65042/132723 [00:00<00:00, 74353.66KB/s]
55%|#####5 | 73560/132723 [00:00<00:00, 77476.16KB/s]
62%|######1 | 81905/132723 [00:01<00:00, 71207.20KB/s]
67%|######7 | 89244/132723 [00:01<00:00, 70829.89KB/s]
74%|#######3 | 97749/132723 [00:01<00:00, 74775.05KB/s]
79%|#######9 | 105368/132723 [00:01<00:00, 46321.47KB/s]
84%|########3 | 111402/132723 [00:01<00:00, 48097.81KB/s]
89%|########9 | 118405/132723 [00:01<00:00, 52891.20KB/s]
96%|########
#5| 126837/132723 [00:01<00:00, 60368.72KB/s]
100%|##########| 132723/132723 [00:02<00:00, 66310.61KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5133/132723 [00:00<00:02, 51322.83KB/s]
9%|9 | 12605/132723 [00:00<00:01, 65083.75KB/s]
14%|#4 | 19114/132723 [00:00<00:01, 63525.31KB/s]
20%|## | 26736/132723 [00:00<00:01, 68461.76KB/s]
25%|##5 | 33593/132723 [00:00<00:01, 55569.31KB/s]
31%|### | 41123/132723 [00:00<00:01, 61343.57KB/s]
36%|###6 | 47927/132723 [00:00<00:01, 45994.32KB/s]
40%|#### | 53240/132723 [00:01<00:02, 39424.71KB/s]
46%|####5 | 60841/132723 [00:01<00:01, 47356.51KB/s]
50%|##### | 66769/132723 [00:01<00:01, 50175.40KB/s]
56%|#####5 | 74236/132723 [00:01<00:01, 56359.29KB/s]
61%|###### | 80692/132723 [00:01<00:00, 58130.74KB/s]
65%|######5 | 86909/132723 [00:01<00:01, 43419.40KB/s]
71%|#######1 | 94605/132723 [00:01<00:00, 50881.44KB/s]
77%|#######6 | 102175/132723 [00:01<00:00, 56866.33KB/s]
83%|########2
| 109789/132723 [00:02<00:00, 61804.67KB/s]
88%|########7 | 116563/132723 [00:02<00:00, 51216.28KB/s]
94%|#########3| 124232/132723 [00:02<00:00, 57232.19KB/s]
99%|#########9| 131945/132723 [00:02<00:00, 62248.31KB/s]
100%|##########| 132723/132723 [00:02<00:00, 54759.09KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 41.547 seconds)
+ **Total running time of the script:** ( 2 minutes 36.713 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 2f46644db..5274677b8 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:50.738** total execution time for **how_to_deploy_models** files:
+**11:32.050** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:01.461 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:57.369 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:41.547 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:36.713 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:58.651 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:58.694 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:41.319 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:35.506 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.732 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:09.184 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.971 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.424 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.368 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.751 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.683 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.403 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 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 f8f1aee8c..74a5d5e98 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.zipb246fdbf-5d17-4a13-8cdf-96bc3ea3de28 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip94d9fc72-cd61-45df-a050-a95a82ee200e 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 063729201..7124527a7 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
=================
-**00:42.137** total execution time for **how_to_extend_tvm** files:
+**00:41.701** 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``) | 00:38.932 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.547 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.244 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.200 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.952 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.945 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.009 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index e87593a1d..bc7b7ed9d 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: 6896us [6896us] (46.62%; 46.62%)
- FoldScaleAxis: 7896us [6us] (53.38%; 53.38%)
- FoldConstant: 7891us [1596us] (53.35%; 99.93%)
- InferType: 6295us [6295us] (42.56%; 79.77%)
+ InferType: 7066us [7066us] (46.47%; 46.47%)
+ FoldScaleAxis: 8140us [6us] (53.53%; 53.53%)
+ FoldConstant: 8133us [1733us] (53.49%; 99.92%)
+ InferType: 6400us [6400us] (42.09%; 78.69%)
@@ -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: 6268us [6268us] (44.69%; 44.69%)
- FoldScaleAxis: 7757us [4us] (55.31%; 55.31%)
- FoldConstant: 7753us [1587us] (55.28%; 99.95%)
- InferType: 6165us [6165us] (43.96%; 79.52%)
+ InferType: 6509us [6509us] (44.86%; 44.86%)
+ FoldScaleAxis: 8000us [5us] (55.14%; 55.14%)
+ FoldConstant: 7995us [1695us] (55.10%; 99.93%)
+ InferType: 6300us [6300us] (43.42%; 78.80%)
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 910e06915..a78aabbb7 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 48.049035 ms
+ Convolution: 42.838868 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 a83c782e3..f90058a20 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.209077 ms
+ conv2d with tensor core: 8.173363 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 03b25841b..41748827c 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: 0.018978
- Baseline: 3.401331
+ Numpy running time: 0.018693
+ Baseline: 3.413802
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.318578
+ Opt1: 0.304378
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.340245
+ Opt2: 0.336063
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.126273
+ Opt3: 0.116909
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109408
+ Opt4: 0.109347
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110941
+ Opt5: 0.111617
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147097
+ Opt6: 0.146532
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 c57cecce1..1590c0e4e 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.895** total execution time for **how_to_optimize_operators** files:
+**00:34.714** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.693 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.352 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.249 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.305 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.954 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.057 | 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 3a70226f0..a8629bd2b 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:18.178** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:04.930** 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``) | 03:26.380 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:18.336 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:24.106 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.648 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:48.174 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:47.079 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:21.564 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.314 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.107 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.791 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.846 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.763 | 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 a0f2fc00e..9d6c3c69d 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
@@ -240,215 +240,439 @@ 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" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [392]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [128]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[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
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- let cse_var_2: int32 = (rc.outer.outer*1568)
- let cse_var_1: int32 = (rc.outer.outer*288)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 21), 81)) && (floormod((threadIdx.x_1 + 21), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (floormod((threadIdx.x_1 + 8), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 7), 9)) && (floormod((threadIdx.x_1 + 63), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1764), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 7), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 16), 81)) && (floormod((threadIdx.x_1 + 16), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 50), 81)) && (floormod((threadIdx.x_1 + 50), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 50), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (floormod((threadIdx.x_1 + 3), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[(threadIdx.x_2*3)] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 2)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 588)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 4), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 589)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 4), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 590)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 4), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 1176)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1177)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 1178)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 1764)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 12), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1765)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 12), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 1766)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 12), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 2352)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 2353)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 2354)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 2940)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 20), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 2941)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 20), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 2942)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 20), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 3528)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 3529)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 3530)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 4116)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 4117)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 4118)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 4704)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 4705)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 4706)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 5292)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1764), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 36), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 5293)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1764), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 36), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 5294)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1764), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 36), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 5880)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 5881)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 5882)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 6468)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2156), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 44), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 6469)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2156), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 44), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 6470)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2156), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 44), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 7056)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 7057)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 7058)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 7644)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2548), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 52), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 7645)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2548), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 52), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 7646)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2548), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 52), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 8232)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 56), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 8233)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 56), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 8234)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 56), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_2 < 132), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*3) + 8820)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2940), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 60), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 8821)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2940), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 60), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 8822)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2940), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 60), 96)*3)) + 2)]
- }
- for (rc.outer.inner: int32, 0, 32) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2304)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4608)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6912)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2305)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4609)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6913)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2306)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4610)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6914)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 288)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2592)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4896)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7200)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 289)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2593)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4897)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7201)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 290)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2594)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4898)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7202)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2307)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4611)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6915)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2308)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4612)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6916)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2309)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4613)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6917)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 291)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2595)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4899)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7203)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 292)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2596)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4900)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7204)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 293)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2597)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4901)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7205)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2310)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4614)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6918)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2311)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4615)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6919)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2312)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4616)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6920)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 294)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2598)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4902)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7206)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 295)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2599)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4903)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7207)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 296)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2600)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4904)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7208)]))
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (ry.outer.outer*7)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [392], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [128], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64512)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32257)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64513)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32258)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64514)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 16)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1176)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 24)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -503,7 +727,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.409 ms
+ Execution time of this operator: 0.254 ms
@@ -553,34 +777,34 @@ 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=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
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_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_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=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ 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=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)
@@ -598,14 +822,14 @@ 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=3)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=196)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -625,167 +849,410 @@ 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__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[9216];
+ extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[392];
+ __shared__ float kernel_shared[128];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((9 <= ((((int)threadIdx.x) + 21) % 81)) && (((((int)threadIdx.x) + 21) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((9 <= ((((int)threadIdx.x) + 8) % 81)) && (((((int)threadIdx.x) + 8) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 81) * 49)) + ((((((int)threadIdx.x) + 8) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) / 9) + 7) % 9)) && (((((int)threadIdx.x) + 63) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1764) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 7) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((9 <= ((((int)threadIdx.x) + 16) % 81)) && (((((int)threadIdx.x) + 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + ((((((int)threadIdx.x) + 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((9 <= ((((int)threadIdx.x) + 50) % 81)) && (((((int)threadIdx.x) + 50) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2156) / 81) * 49)) + ((((((int)threadIdx.x) + 50) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((9 <= ((((int)threadIdx.x) + 3) % 81)) && (((((int)threadIdx.x) + 3) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + ((((((int)threadIdx.x) + 3) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 44) {
- pad_temp_shared[(((int)threadIdx.x) + 2548)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2548) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 3)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 588)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 589)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 590)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1176)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1177)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1178)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1764)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 12) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1765)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 12) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1766)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 12) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2352)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 2353)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2354)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2940)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 20) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 2941)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 20) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2942)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 20) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 3528)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 24) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 3529)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 24) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 3530)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 24) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 4116)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 28) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 4117)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 28) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 4118)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 28) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 4704)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 4705)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 4706)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 5292)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 36) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 5293)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 36) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 5294)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 36) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 5880)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 5881)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 5882)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 6468)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 44) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 6469)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 44) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 6470)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 44) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 7056)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 48) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 7057)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 48) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 7058)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 48) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 7644)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 52) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 7645)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 52) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 7646)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 52) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 8232)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 8233)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 8234)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) % 96) * 3)) + 2)];
- if (((int)threadIdx.x) < 132) {
- kernel_shared[((((int)threadIdx.x) * 3) + 8820)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 60) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 8821)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 60) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 8822)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 60) % 96) * 3)) + 2)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2304)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4608)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6912)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2305)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4609)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6913)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2306)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4610)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6914)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 288)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2592)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4896)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7200)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 289)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2593)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4897)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 290)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2594)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4898)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7202)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2307)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4611)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6915)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2308)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4612)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6916)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2309)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4613)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6917)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 291)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2595)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4899)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7203)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 292)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2596)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4900)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7204)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 293)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2597)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4901)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7205)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2310)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4614)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6918)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2311)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4615)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6919)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2312)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4616)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6920)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 294)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2598)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4902)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7206)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 295)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2599)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4903)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7207)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 296)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2600)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4904)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7208)]));
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32256)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64512)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32257)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64513)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32258)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64514)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1176)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 24)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -847,7 +1314,7 @@ 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 26.380 seconds)
+ **Total running time of the script:** ( 3 minutes 18.336 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 d469a9427..e759576bc 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)
- 9.9503 9.9650 9.9681 9.9179 0.0230
+ 9.8647 9.8428 9.9172 9.8341 0.0373
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 c1bd07bcd..cee9f25f1 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)
- 756.0070 756.2754 756.3648 755.3809 0.4443
+ 753.4929 753.2963 753.9879 753.1944 0.3525
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 24.106 seconds)
+ **Total running time of the script:** ( 1 minutes 22.648 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 6998b196f..fc2dd0be3 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
@@ -397,31 +397,29 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), 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_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [256], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
- }
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global;
+ for (i1.outer: int32, 0, 32) {
+ for (i.outer.inner: int32, 0, 16) {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
+ for (i.inner: int32, 0, 8) {
+ for (j: int32, 0, 16) {
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ let cse_var_1: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
- }
+ }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_2: int32 = ((i0.inner*512) + (i1.outer*16))
+ compute[ramp(cse_var_2, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -476,7 +474,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.572 ms
+ Execution time of this operator: 1.520 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 f91f7813e..ec3f90dea 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:46.422** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.411** 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``) | 00:46.385 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.375 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.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 56f2cc2ce..dd18d9fac 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: 201.90/201.90 result: MeasureResult(costs=(0.0011465961666666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1001603603363037, timestamp=1662046198.3345554) [('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: 0.00/201.90 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 80.75/80.75 result: MeasureResult(costs=(0.0028669616285714283,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8190627098083496, timestamp=1662054114.377857) [('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: 0.00/80.75 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.26/260.26 result: MeasureResult(costs=(0.0008895155248618784,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7303051948547363, timestamp=1662046199.2413735) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.72/260.72 result: MeasureResult(costs=(0.0008879196906077348,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.69096040725708, timestamp=1662054115.253785) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.72 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: 5.30/260.26 result: MeasureResult(costs=(0.043684947,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8386874198913574, timestamp=1662046203.8067925) [('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: 3.35/260.26 result: MeasureResult(costs=(0.069142329,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.547529935836792, timestamp=1662046205.0482953) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.27/260.72 result: MeasureResult(costs=(0.043939778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8757946491241455, timestamp=1662054119.8422925) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.36/260.72 result: MeasureResult(costs=(0.0689503045,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5667665004730225, timestamp=1662054121.0828333) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/260.72 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: 28.06/260.26 result: MeasureResult(costs=(0.008248774928571428,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.29433274269104, timestamp=1662046216.103824) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 28.03/260.72 result: MeasureResult(costs=(0.008257903214285715,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2839818000793457, timestamp=1662054132.120746) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.72 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: 0.001269
+ Time cost of this operator: 0.001273
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 e83e7fdcb..46d0ef678 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 314.5 98.739 (1, 2, 10, 10, 3) 2 1 [314.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.033 0.952 (1, 6, 10, 10) 1 1 [3.033]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.983 0.309 (1, 1, 10, 10, 3) 1 1 [0.983]
- Total_time - 318.516 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.1 98.738 (1, 2, 10, 10, 3) 2 1 [311.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.958 (1, 6, 10, 10) 1 1 [3.017]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 0.304 (1, 1, 10, 10, 3) 1 1 [0.957]
+ Total_time - 315.075 - - - - -
@@ -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 289.7 98.635 (1, 2, 10, 10, 3) 2 1 [289.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.036 1.034 (1, 6, 10, 10) 1 1 [3.036]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.331 (1, 1, 10, 10, 3) 1 1 [0.972]
- Total_time - 293.709 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.812 96.675 (1, 6, 10, 10, 1) 2 1 [79.812]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.767 2.14 (1, 6, 10, 10) 1 1 [1.767]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 1.185 (1, 1, 10, 10, 3) 1 1 [0.978]
+ Total_time - 82.558 - - - - -
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 0f9c5bf58..5aca3b9d7 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/tmpkbf_xhfy/images/random'
+ '/tmp/tmp_mmaw2it/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpkbf_xhfy/images/target contains 8144 images
- /tmp/tmpkbf_xhfy/images/random contains 5000 images
+ /tmp/tmp_mmaw2it/images/target contains 8144 images
+ /tmp/tmp_mmaw2it/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 56s - loss: 0.2021 - accuracy: 0.9264 - val_loss: 0.1240 - val_accuracy: 0.9577
+ 328/328 - 56s - loss: 0.2197 - accuracy: 0.9250 - val_loss: 0.1481 - val_accuracy: 0.9558
Epoch 2/3
- 328/328 - 53s - loss: 0.0972 - accuracy: 0.9633 - val_loss: 0.1237 - val_accuracy: 0.9577
+ 328/328 - 52s - loss: 0.1012 - accuracy: 0.9616 - val_loss: 0.1194 - val_accuracy: 0.9596
Epoch 3/3
- 328/328 - 53s - loss: 0.0665 - accuracy: 0.9754 - val_loss: 0.1077 - val_accuracy: 0.9671
+ 328/328 - 52s - loss: 0.0672 - accuracy: 0.9751 - val_loss: 0.1141 - val_accuracy: 0.9630
- <keras.callbacks.History object at 0x7f1490619bd0>
+ <keras.callbacks.History object at 0x7f11784f4f10>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 10.483 seconds)
+ **Total running time of the script:** ( 5 minutes 10.137 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 8925b067e..f37937936 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**06:04.849** total execution time for **how_to_work_with_microtvm** files:
+**06:03.680** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:10.483 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:10.137 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.129 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.128 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.852 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.122 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.382 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.291 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index f5021ddf0..e931d0c2a 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
=================
-**00:43.407** total execution time for **how_to_work_with_relay** files:
+**00:43.040** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.748 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.558 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.317 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.910 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.335 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.565 | 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 50f606045..815f9a520 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 0x7f1491d35830>
+ <function my_cuda_math_rule at 0x7f10f6f329e0>
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 5b4fb37ba..55c75509c 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
@@ -5,20 +5,20 @@
Computation times
=================
-**00:04.144** total execution time for **how_to_work_with_schedules** files:
+**00:04.173** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.920 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.939 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.982 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.536 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.540 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.519 | 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_extern_op.py` (``extern_op.py``) | 00:00.103 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.100 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.044 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 c97a2367e..7b481119e 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/tmpe5wr_w3p/input0.cc'\nsource_filename = \"/tmp/tmpe5wr_w3p/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/tmpl0dhmv6r/input0.cc'\nsource_filename = \"/tmp/tmpl0dhmv6r/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 6cf3b6413..dd0325784 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
=================
-**00:22.198** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.304** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.191 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.297 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 81d93732d..e2a85493d 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 23.86s!
+ resnet18_v1 inference graph built in 23.02s!
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 666d9224c..bc5a5bc09 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:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.62s!
+ yolov3-tiny inference graph built in 16.16s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index 0f36d7376..464c6d810 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:33.653** total execution time for **topic_vta_tutorials_frontend** files:
+**01:32.597** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.474 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.153 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.179 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.444 | 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 4956147a2..e61e5ef4d 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
=================
-**00:03.259** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.317** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.861 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.907 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.398 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.409 | 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 399d20198..3f12a7041 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.708** total execution time for **topic_vta_tutorials** files:
+**00:00.746** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.374 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.398 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.334 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.347 | 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 90f1c1704..7e979d70f 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.262 ms
+ Execution time of this operator: 94.447 ms
@@ -442,11 +442,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 5.533 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 f3dbb1edc..766d1ea58 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.33/10.33 result: MeasureResult(costs=(0.0259806908,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.553368091583252, timestamp=1662044930.8355842) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.95/10.33 result: MeasureResult(costs=(0.0909442286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.607630968093872, timestamp=1662044932.4553208) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0227978484,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5645833015441895, timestamp=1662044933.524316) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.86/11.77 result: MeasureResult(costs=(0.1443764272,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.426344394683838, timestamp=1662044936.5437012) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.65/11.77 result: MeasureResult(costs=(0.073616742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3122961521148682, timestamp=1662044938.5254374) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.75/11.77 result: MeasureResult(costs=(0.15349440939999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.635594367980957, timestamp=1662044941.2042146) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.81/11.77 result: MeasureResult(costs=(0.330520309,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.405975818634033, timestamp=1662044946.6555026) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.38/11.77 result: MeasureResult(costs=(0.025863171,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5585572719573975, timestamp=1662044947.2317955) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.95/11.77 result: MeasureResult(costs=(0.1379159984,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3240528106689453, timestamp=1662044949.6758037) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.52/11.77 result: MeasureResult(costs=(0.1063534746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.805710792541504, timestamp=1662044951.5397818) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.65/9.65 result: MeasureResult(costs=(0.027818264399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5809295177459717, timestamp=1662052883.3688154) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.25/9.65 result: MeasureResult(costs=(0.119499149,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.064157485961914, timestamp=1662052885.9779427) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.81/11.81 result: MeasureResult(costs=(0.02273791,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6039459705352783, timestamp=1662052886.5468912) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.64/11.81 result: MeasureResult(costs=(0.1637648022,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7406458854675293, timestamp=1662052889.8632522) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.62/11.81 result: MeasureResult(costs=(0.074074002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.322547435760498, timestamp=1662052891.316292) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.61/11.81 result: MeasureResult(costs=(0.166580006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7907514572143555, timestamp=1662052894.6801717) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.81/11.81 result: MeasureResult(costs=(0.3312716924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.42108154296875, timestamp=1662052900.1463711) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 9.04/11.81 result: MeasureResult(costs=(0.0296913874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6199190616607666, timestamp=1662052900.7870317) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.48/11.81 result: MeasureResult(costs=(0.181191088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0061700344085693, timestamp=1662052903.9128928) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.62/11.81 result: MeasureResult(costs=(0.1025708474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7484710216522217, timestamp=1662052905.7198098) [('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 c1811f1cd..07b903187 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': 496.1427404700089, 'median': 496.0948851000012, 'std': 0.6810259431842657}
+ {'mean': 493.6193124900001, 'median': 493.7237737500027, 'std': 0.820370130637166}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.51/ 17.51 GFLOPS | Progress: (4/20) | 6.43 s
[Task 1/25] Current/Best: 6.16/ 17.51 GFLOPS | Progress: (8/20) | 9.49 s
[Task 1/25] Current/Best: 11.53/ 22.78 GFLOPS | Progress: (12/20) | 11.98 s
[Task 1/25] Current/Best: 16.41/ 22.78 GFLOPS | Progress: (16/20) | 13.69 s
[Task 1/25] Current/Best: 11.54/ 23.80 GFLOPS | Progress: (20/20) | 15.46 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.20/ 13.18 GFLOPS | Progress: (4/20) | 3.94 s
[Task 2/25] Current/Best: 14.02/ 18.15 GFLOPS | Progress: (8/20) | 5.26 s
[Task 2/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (12/20) | 6.63 s
[Task 2/25] Current/Best: 12.33/ 20.72 GFLOPS | Progress: (16/20) | 7.90 s
[Task 2/25] Current/Best: 20.37/ 20.72 GFLOPS | Progress: (20/20) | 9.52 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/ 10.79 GFLOPS | Progress: (4/20) | 5.92 s
[Task 3/25] Current/Best: 15.26/ 16.73 GFLOPS | Progress: (8/20) | 7.86 s
[Task 3/25] Current/Best: 14.91/ 16.73 GFLOPS | Progress: (12/20) | 9.61 s
[Task 3/25] Current/Best: 7.21/ 23.64 GFLOPS | Progress: (16/20) | 11.54 s
[Task 3/25] Current/Best: 12.56/ 23.64 GFLOPS | Progress: (20/20) | 16.13 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.46/ 19.49 GFLOPS | Progress: (4/20) | 2.48 s
[Task 4/25] Current/Best: 6.80/ 19.49 GFLOPS | Progress: (8/20) | 7.24 s
[Task 4/25] Current/Best: 21.97/ 21.97 GFLOPS | Progress: (12/20) | 12.27 s
[Task 4/25] Current/Best: 17.49/ 21.97 GFLOPS | Progress: (16/20) | 14.67 s
[Task 4/25] Current/Best: 13.34/ 21.97 GFLOPS | Progress: (20/20) | 16.79 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.55/ 10.25 GFLOPS | Progress: (4/20) | 2.65 s
[Task 5/25] Current/Best: 11.69/ 11.83 GFLOPS | Progress: (8/20) | 4.72 s
[Task 5/25] Current/Best: 10.64/ 17.92 GFLOPS | Progress: (12/20) | 7.91 s
[Task 5/25] Current/Best: 10.88/ 22.52 GFLOPS | Progress: (16/20) | 9.35 s
[Task 5/25] Current/Best: 12.03/ 22.52 GFLOPS | Progress: (20/20) | 11.28 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.11/ 20.09 GFLOPS | Progress: (4/20) | 4.15 s
[Task 6/25] Current/Best: 18.79/ 20.09 GFLOPS | Progress: (8/20) | 5.94 s
[Task 6/25] Current/Best: 13.22/ 20.09 GFLOPS | Progress: (12/20) | 7.91 s
[Task 6/25] Current/Best: 20.03/ 20.09 GFLOPS | Progress: (16/20) | 10.16 s
[Task 6/25] Current/Best: 3.73/ 20.09 GFLOPS | Progress: (20/20) | 12.71 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.75/ 12.88 GFLOPS | Progress: (4/20) | 3.70 s
[Task 7/25] Current/Best: 19.95/ 21.19 GFLOPS | Progress: (8/20) | 5.25 s
[Task 7/25] Current/Best: 15.96/ 21.19 GFLOPS | Progress: (12/20) | 7.18 s
[Task 7/25] Current/Best: 12.18/ 21.19 GFLOPS | Progress: (16/20) | 9.23 s
[Task 7/25] Current/Best: 6.37/ 21.74 GFLOPS | Progress: (20/20) | 11.70 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.08/ 14.16 GFLOPS | Progress: (4/20) | 2.95 s
[Task 8/25] Current/Best: 9.16/ 14.16 GFLOPS | Progress: (8/20) | 8.12 s
[Task 8/25] Current/Best: 13.16/ 14.16 GFLOPS | Progress: (12/20) | 14.69 s
[Task 8/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (16/20) | 16.81 s
[Task 8/25] Current/Best: 19.73/ 19.73 GFLOPS | Progress: (20/20) | 23.89 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.29/ 15.56 GFLOPS | Progress: (4/20) | 11.97 s
[Task 9/25] Current/Best: 23.27/ 23.27 GFLOPS | Progress: (8/20) | 13.75 s
[Task 9/25] Current/Best: 8.22/ 23.27 GFLOPS | Progress: (12/20) | 16.28 s
[Task 9/25] Current/Best: 17.77/ 23.27 GFLOPS | Progress: (16/20) | 19.14 s
[Task 9/25] Current/Best: 8.96/ 23.27 GFLOPS | Progress: (20/20) | 27.75 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.34/ 18.34 GFLOPS | Progress: (4/20) | 2.63 s
[Task 10/25] Current/Best: 15.60/ 18.34 GFLOPS | Progress: (8/20) | 4.30 s
[Task 10/25] Current/Best: 12.83/ 18.87 GFLOPS | Progress: (12/20) | 5.86 s
[Task 10/25] Current/Best: 19.08/ 20.23 GFLOPS | Progress: (16/20) | 6.98 s
[Task 10/25] Current/Best: 8.76/ 20.23 GFLOPS | Progress: (20/20
) | 8.52 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.29/ 18.11 GFLOPS | Progress: (4/20) | 3.43 s
[Task 11/25] Current/Best: 16.86/ 18.11 GFLOPS | Progress: (8/20) | 6.28 s
[Task 11/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (12/20) | 8.33 s
[Task 11/25] Current/Best: 13.44/ 20.96 GFLOPS | Progress: (16/20) | 11.21 s
[Task 11/25] Current/Best: 19.41/ 21.64 GFLOPS | Progress: (20/20) | 13.32 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/ 18.00 GFLOPS | Progress: (4/20) | 5.80 s
[Task 12/25] Current/Best: 5.16/ 18.00 GFLOPS | Progress: (8/20) | 9.78 s
[Task 12/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (12/20) | 11.80 s
[Task 12/25] Current/Best: 15.07/ 19.13 GFLOPS | Progress: (16/20) | 14.73 s
[Task 12/25] Current/Best: 15.15/ 19.13 GFLOPS | Progress: (20/20) | 16.65 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.74/ 17.10 GFLOPS | Progress: (4/20) | 3.85 s
[Task 13/25] Current/Best: 15.85/ 20.80 GFLOPS | Progress: (8/20) | 6.44 s
[Task 13/25] Current/Best: 19.54/ 21.80 GFLOPS | Progress: (12/20) | 9.55 s
[Task 13/25] Current/Best: 12.22/ 21.80 GFLOPS | Progress: (16/20) | 13.04 s
[Task 13/25] Current/Best: 18.80/ 21.80 GFLOPS | Progress: (20/20) | 15.36 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.78/ 13.78 GFLOPS | Progress: (4/20) | 3.46 s
[Task 14/25] Current/Best: 6.08/ 13.78 GFLOPS | Progress: (8/20) | 5.63 s
[Task 14/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (12/20) | 8.33 s
[Task 14/25] Current/Best: 17.05/ 20.06 GFLOPS | Progress: (16/20) | 10.00 s Done.
-
[Task 14/25] Current/Best: 17.23/ 20.06 GFLOPS | Progress: (20/20) | 11.76 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.15/ 17.64 GFLOPS | Progress: (4/20) | 2.82 s
[Task 15/25] Current/Best: 14.19/ 17.83 GFLOPS | Progress: (8/20) | 4.13 s
[Task 15/25] Current/Best: 10.39/ 22.35 GFLOPS | Progress: (12/20) | 6.37 s
[Task 15/25] Current/Best: 20.34/ 22.35 GFLOPS | Progress: (16/20) | 9.99 s
[Task 15/25] Current/Best: 9.69/ 22.35 GFLOPS | Progress: (20/20) | 11.02 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (4/20) | 3.17 s
[Task 16/25] Current/Best: 3.04/ 20.61 GFLOPS | Progress: (8/20) | 4.78 s
[Task 16/25] Current/Best: 19.29/ 20.61 GFLOPS | Progress: (12/20) | 5.99 s
[Task 16/25] Current/Best: 17.69/ 20.61 GFLOPS | Progress: (16/20) |
7.38 s
[Task 16/25] Current/Best: 10.01/ 21.47 GFLOPS | Progress: (20/20) | 9.54 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.20/ 18.36 GFLOPS | Progress: (4/20) | 4.88 s
[Task 17/25] Current/Best: 14.45/ 23.41 GFLOPS | Progress: (8/20) | 7.75 s
[Task 17/25] Current/Best: 17.87/ 23.41 GFLOPS | Progress: (12/20) | 9.82 s
[Task 17/25] Current/Best: 16.48/ 23.41 GFLOPS | Progress: (16/20) | 12.05 s
[Task 17/25] Current/Best: 10.03/ 23.41 GFLOPS | Progress: (20/20) | 14.21 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.55/ 18.07 GFLOPS | Progress: (4/20) | 3.82 s
[Task 18/25] Current/Best: 10.61/ 19.62 GFLOPS | Progress: (8/20) | 7.50 s
[Task 18/25] Current/Best: 18.99/ 19.62 GFLOPS | Progress: (12/20) | 9.45 s
[Task 18/25] Current/Best: 10.00/ 19.62 GFLOPS | Progress: (16/20) | 13.28 s
[Task 18/25] Current/Best: 20.51/ 20.51 GFLOPS | Progress: (20/20) | 14.80 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.14/ 20.08 GFLOPS | Progress: (4/20) | 6.20 s
[Task 19/25] Current/Best: 2.69/ 20.08 GFLOPS | Progress: (8/20) | 9.51 s
[Task 19/25] Current/Best: 19.54/ 21.22 GFLOPS | Progress: (12/20) | 12.49 s
[Task 19/25] Current/Best: 15.51/ 21.22 GFLOPS | Progress: (16/20) | 15.45 s
[Task 19/25] Current/Best: 2.70/ 22.99 GFLOPS | Progress: (20/20) | 18.25 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.99/ 15.19 GFLOPS | Progress: (4/20) | 3.44 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (4/20) | 5.83 s
[Task 1/25] Current/Best: 6.16/ 17.60 GFLOPS | Progress: (8/20) | 9.25 s
[Task 1/25] Current/Best: 11.53/ 22.84 GFLOPS | Progress: (12/20) | 11.73 s
[Task 1/25] Current/Best: 16.56/ 22.84 GFLOPS | Progress: (16/20) | 13.42 s
[Task 1/25] Current/Best: 11.61/ 23.84 GFLOPS | Progress: (20/20) | 15.17 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.25/ 12.85 GFLOPS | Progress: (4/20) | 3.74 s
[Task 2/25] Current/Best: 14.17/ 18.39 GFLOPS | Progress: (8/20) | 5.03 s
[Task 2/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (12/20) | 6.36 s
[Task 2/25] Current/Best: 12.24/ 20.59 GFLOPS | Progress: (16/20) | 7.61 s
[Task 2/25] Current/Best: 19.35/ 20.59 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: 1.63/ 10.84 GFLOPS | Progress: (4/20) | 5.86 s
[Task 3/25] Current/Best: 15.02/ 16.82 GFLOPS | Progress: (8/20) | 7.81 s
[Task 3/25] Current/Best: 14.99/ 16.82 GFLOPS | Progress: (12/20) | 9.52 s
[Task 3/25] Current/Best: 7.23/ 23.76 GFLOPS | Progress: (16/20) | 11.43 s
[Task 3/25] Current/Best: 12.06/ 23.76 GFLOPS | Progress: (20/20) | 15.98 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.56/ 20.35 GFLOPS | Progress: (4/20) | 2.41 s
[Task 4/25] Current/Best: 6.78/ 20.35 GFLOPS | Progress: (8/20) | 7.08 s
[Task 4/25] Current/Best: 22.42/ 22.42 GFLOPS | Progress: (12/20) | 12.02 s
[Task 4/25] Current/Best: 16.21/ 22.42 GFLOPS | Progress: (16/20) | 14.41 s
[Task 4/25] Current/Best: 13.25/ 22.42 GFLOPS | Progress: (20/20) | 16.52 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.57/ 10.31 GFLOPS | Progress: (4/20) | 2.64 s
[Task 5/25] Current/Best: 11.76/ 12.70 GFLOPS | Progress: (8/20) | 4.73 s
[Task 5/25] Current/Best: 11.50/ 18.05 GFLOPS | Progress: (12/20) | 7.78 s
[Task 5/25] Current/Best: 11.68/ 22.56 GFLOPS | Progress: (16/20) | 9.24 s
[Task 5/25] Current/Best: 12.11/ 22.56 GFLOPS | Progress: (20/20) | 11.13 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.01/ 20.11 GFLOPS | Progress: (4/20) | 4.12 s
[Task 6/25] Current/Best: 18.87/ 20.11 GFLOPS | Progress: (8/20) | 5.92 s
[Task 6/25] Current/Best: 13.34/ 20.11 GFLOPS | Progress: (12/20) | 7.88 s
[Task 6/25] Current/Best: 20.00/ 20.11 GFLOPS | Progress: (16/20) | 10.15 s
[Task 6/25] Current/Best: 3.73/ 20.11 GFLOPS | Progress: (20/20) | 12.66 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.92/ 12.44 GFLOPS | Progress: (4/20) | 3.65 s
[Task 7/25] Current/Best: 20.00/ 21.18 GFLOPS | Progress: (8/20) | 5.17 s
[Task 7/25] Current/Best: 16.13/ 21.18 GFLOPS | Progress: (12/20) | 7.06 s
[Task 7/25] Current/Best: 12.21/ 21.18 GFLOPS | Progress: (16/20) | 9.10 s
[Task 7/25] Current/Best: 6.37/ 21.85 GFLOPS | Progress: (20/20) | 11.56 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.70/ 13.81 GFLOPS | Progress: (4/20) | 2.92 s
[Task 8/25] Current/Best: 9.35/ 13.81 GFLOPS | Progress: (8/20) | 8.03 s
[Task 8/25] Current/Best: 13.06/ 13.81 GFLOPS | Progress: (12/20) | 14.52 s
[Task 8/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (16/20) | 16.65 s
[Task 8/25] Current/Best: 19.30/ 19.30 GFLOPS | Progress: (20/20) | 23.64 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.37/ 15.79 GFLOPS | Progress: (4/20) | 11.99 s
[Task 9/25] Current/Best: 23.45/ 23.45 GFLOPS | Progress: (8/20) | 13.77 s
[Task 9/25] Current/Best: 8.30/ 23.45 GFLOPS | Progress: (12/20) | 16.29 s
[Task 9/25] Current/Best: 17.90/ 23.45 GFLOPS | Progress: (16/20) | 19.12 s
[Task 9/25] Current/Best: 9.21/ 23.45 GFLOPS | Progress: (20/20) | 27.55 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (4/20) | 2.60 s
[Task 10/25] Current/Best: 15.63/ 18.13 GFLOPS | Progress: (8/20) | 4.24 s
[Task 10/25] Current/Best: 12.64/ 18.89 GFLOPS | Progress: (12/20) | 5.79 s
[Task 10/25] Current/Best: 19.19/ 20.40 GFLOPS | Progress: (16/20) | 6.91 s
[Task 10/25] Current/Best: 8.82/ 20.40 GFLOPS | Progress: (20/20
) | 8.44 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.29/ 18.20 GFLOPS | Progress: (4/20) | 3.40 s
[Task 11/25] Current/Best: 16.64/ 18.20 GFLOPS | Progress: (8/20) | 6.19 s
[Task 11/25] Current/Best: 16.21/ 18.20 GFLOPS | Progress: (12/20) | 8.31 s
[Task 11/25] Current/Best: 13.44/ 21.01 GFLOPS | Progress: (16/20) | 11.24 s
[Task 11/25] Current/Best: 19.46/ 21.53 GFLOPS | Progress: (20/20) | 13.34 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 17.99 GFLOPS | Progress: (4/20) | 5.71 s
[Task 12/25] Current/Best: 5.19/ 17.99 GFLOPS | Progress: (8/20) | 9.61 s
[Task 12/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (12/20) | 11.65 s
[Task 12/25] Current/Best: 15.32/ 18.91 GFLOPS | Progress: (16/20) | 14.56 s
[Task 12/25] Current/Best: 15.14/ 18.91 GFLOPS | Progress: (20/20) | 16.50 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.69/ 17.31 GFLOPS | Progress: (4/20) | 3.77 s
[Task 13/25] Current/Best: 15.72/ 20.90 GFLOPS | Progress: (8/20) | 6.35 s
[Task 13/25] Current/Best: 19.52/ 21.97 GFLOPS | Progress: (12/20) | 9.39 s
[Task 13/25] Current/Best: 12.30/ 21.97 GFLOPS | Progress: (16/20) | 12.87 s
[Task 13/25] Current/Best: 18.51/ 21.97 GFLOPS | Progress: (20/20) | 15.19 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.32/ 13.32 GFLOPS | Progress: (4/20) | 3.47 s
[Task 14/25] Current/Best: 6.11/ 13.32 GFLOPS | Progress: (8/20) | 5.64 s
[Task 14/25] Current/Best: 20.15/ 20.15 GFLOPS | Progress: (12/20) | 8.31 s
[Task 14/25] Current/Best: 17.02/ 20.15 GFLOPS | Progress: (16/20) | 9.95 s Done.
+
[Task 14/25] Current/Best: 17.32/ 20.15 GFLOPS | Progress: (20/20) | 11.70 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.09/ 16.09 GFLOPS | Progress: (4/20) | 2.77 s
[Task 15/25] Current/Best: 12.68/ 17.97 GFLOPS | Progress: (8/20) | 4.08 s
[Task 15/25] Current/Best: 10.38/ 22.28 GFLOPS | Progress: (12/20) | 6.31 s
[Task 15/25] Current/Best: 20.32/ 22.28 GFLOPS | Progress: (16/20) | 9.48 s
[Task 15/25] Current/Best: 9.69/ 22.28 GFLOPS | Progress: (20/20) | 10.50 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (4/20) | 3.01 s
[Task 16/25] Current/Best: 3.03/ 20.58 GFLOPS | Progress: (8/20) | 4.62 s
[Task 16/25] Current/Best: 19.16/ 20.58 GFLOPS | Progress: (12/20) | 5.84 s
[Task 16/25] Current/Best: 18.06/ 20.58 GFLOPS | Progress: (16/20) |
7.23 s
[Task 16/25] Current/Best: 9.97/ 22.35 GFLOPS | Progress: (20/20) | 9.39 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.50/ 18.37 GFLOPS | Progress: (4/20) | 4.80 s
[Task 17/25] Current/Best: 14.23/ 23.34 GFLOPS | Progress: (8/20) | 7.69 s
[Task 17/25] Current/Best: 16.80/ 23.34 GFLOPS | Progress: (12/20) | 9.77 s
[Task 17/25] Current/Best: 16.47/ 23.34 GFLOPS | Progress: (16/20) | 12.02 s
[Task 17/25] Current/Best: 10.02/ 23.34 GFLOPS | Progress: (20/20) | 14.20 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.44/ 16.71 GFLOPS | Progress: (4/20) | 3.87 s
[Task 18/25] Current/Best: 10.56/ 18.84 GFLOPS | Progress: (8/20) | 7.54 s
[Task 18/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 9.47 s
[Task 18/25] Current/Best: 9.97/ 19.28 GFLOPS | Progress: (16/20) | 13.37 s
[Task 18/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (20/20) | 14.88 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.10/ 20.13 GFLOPS | Progress: (4/20) | 6.19 s
[Task 19/25] Current/Best: 2.69/ 20.13 GFLOPS | Progress: (8/20) | 9.52 s
[Task 19/25] Current/Best: 19.68/ 21.48 GFLOPS | Progress: (12/20) | 12.45 s
[Task 19/25] Current/Best: 15.49/ 22.58 GFLOPS | Progress: (16/20) | 15.51 s
[Task 19/25] Current/Best: 2.70/ 23.08 GFLOPS | Progress: (20/20) | 18.30 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.75/ 15.20 GFLOPS | Progress: (4/20) | 3.40 s Done.
Done.
-
[Task 20/25] Current/Best: 10.06/ 15.19 GFLOPS | Progress: (8/20) | 6.87 s
[Task 20/25] Current/Best: 2.32/ 16.60 GFLOPS | Progress: (12/20) | 10.81 s
[Task 20/25] Current/Best: 12.28/ 16.60 GFLOPS | Progress: (16/20) | 14.83 s
[Task 20/25] Current/Best: 12.12/ 21.53 GFLOPS | Progress: (20/20) | 16.96 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.58 GFLOPS | Progress: (4/20) | 3.33 s
[Task 21/25] Current/Best: 14.44/ 17.58 GFLOPS | Progress: (8/20) | 4.94 s
[Task 21/25] Current/Best: 1.61/ 17.58 GFLOPS | Progress: (12/20) | 7.12 s
[Task 21/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (16/20) | 10.69 s
[Task 21/25] Current/Best: 4.47/ 18.07 GFLOPS | Progress: (20/20) | 18.07 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
) | 2.74 s
[Task 22/25] Current/Best: 9.03/ 21.63 GFLOPS | Progress: (8/20) | 4.81 s
[Task 22/25] Current/Best: 19.74/ 21.63 GFLOPS | Progress: (12/20) | 7.18 s
[Task 22/25] Current/Best: 15.31/ 21.63 GFLOPS | Progress: (16/20) | 9.30 s
[Task 22/25] Current/Best: 14.58/ 21.63 GFLOPS | Progress: (20/20) | 11.06 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.43/ 20.17 GFLOPS | Progress: (4/20) | 3.29 s
[Task 23/25] Current/Best: 15.71/ 20.17 GFLOPS | Progress: (8/20) | 6.75 s
[Task 23/25] Current/Best: 20.88/ 21.31 GFLOPS | Progress: (12/20) | 8.63 s
[Task 23/25] Current/Best: 6.11/ 21.31 GFLOPS | Progress: (16/20) | 15.88 s
[Task 23/25] Current/Best: 7.64/ 21.31 GFLOPS | Progress: (20/20) | 20.18 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.57/ 8.57 GFLOPS | Progress: (4/20) | 11.84 s
[Task 24/25] Current/Best: 3.54/ 8.57 GFLOPS | Progress: (8/20) | 23.09 s
[Task 24/25] Current/Best: 4.30/ 8.57 GFLOPS | Progress: (12/20) | 33.83 s Done.
-
[Task 24/25] Current/Best: 7.16/ 8.84 GFLOPS | Progress: (16/20) | 39.56 s
[Task 24/25] Current/Best: 3.32/ 8.84 GFLOPS | Progress: (20/20) | 45.66 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/ 2.93 GFLOPS | Progress: (4/20) | 11.65 s
[Task 25/25] Current/Best: 5.63/ 7.74 GFLOPS | Progress: (8/20) | 23.00 s
[Task 25/25] Current/Best: 5.69/ 7.74 GFLOPS | Progress: (12/20) | 34.32 s
[Task 25/25] Current/Best: 5.75/ 8.59 GFLOPS | Progress: (16/20) | 36.11 s
[Task 25/25] Current/Best: 2.90/ 8.79 GFLOPS | Progress: (20/20) | 46.83 s
+
[Task 20/25] Current/Best: 9.73/ 15.20 GFLOPS | Progress: (8/20) | 6.80 s
[Task 20/25] Current/Best: 2.30/ 16.43 GFLOPS | Progress: (12/20) | 10.69 s
[Task 20/25] Current/Best: 12.35/ 16.43 GFLOPS | Progress: (16/20) | 14.65 s
[Task 20/25] Current/Best: 12.50/ 22.26 GFLOPS | Progress: (20/20) | 16.77 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.71 GFLOPS | Progress: (4/20) | 3.30 s
[Task 21/25] Current/Best: 14.68/ 17.71 GFLOPS | Progress: (8/20) | 4.89 s
[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 7.00 s
[Task 21/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (16/20) | 10.55 s
[Task 21/25] Current/Best: 4.47/ 18.04 GFLOPS | Progress: (20/20) | 17.87 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.02 GFLOPS | Progress: (4/20
) | 2.70 s
[Task 22/25] Current/Best: 8.68/ 22.01 GFLOPS | Progress: (8/20) | 4.75 s
[Task 22/25] Current/Best: 19.98/ 22.01 GFLOPS | Progress: (12/20) | 7.14 s
[Task 22/25] Current/Best: 15.61/ 22.01 GFLOPS | Progress: (16/20) | 9.31 s
[Task 22/25] Current/Best: 14.05/ 22.01 GFLOPS | Progress: (20/20) | 10.99 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.68/ 20.73 GFLOPS | Progress: (4/20) | 3.30 s
[Task 23/25] Current/Best: 13.76/ 20.73 GFLOPS | Progress: (8/20) | 6.80 s
[Task 23/25] Current/Best: 20.94/ 21.42 GFLOPS | Progress: (12/20) | 8.64 s
[Task 23/25] Current/Best: 6.40/ 21.42 GFLOPS | Progress: (16/20) | 15.66 s
[Task 23/25] Current/Best: 7.91/ 21.42 GFLOPS | Progress: (20/20) | 19.88 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.47/ 8.47 GFLOPS | Progress: (4/20) | 11.82 s
[Task 24/25] Current/Best: 2.15/ 8.47 GFLOPS | Progress: (8/20) | 22.86 s
[Task 24/25] Current/Best: 4.27/ 8.47 GFLOPS | Progress: (12/20) | 34.41 s Done.
+
[Task 24/25] Current/Best: 6.20/ 8.57 GFLOPS | Progress: (16/20) | 40.09 s
[Task 24/25] Current/Best: 3.37/ 8.82 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/ 2.94 GFLOPS | Progress: (4/20) | 11.63 s
[Task 25/25] Current/Best: 5.90/ 7.84 GFLOPS | Progress: (8/20) | 22.90 s
[Task 25/25] Current/Best: 6.01/ 7.84 GFLOPS | Progress: (12/20) | 34.39 s
[Task 25/25] Current/Best: 5.85/ 8.49 GFLOPS | Progress: (16/20) | 36.11 s
[Task 25/25] Current/Best: 2.89/ 8.81 GFLOPS | Progress: (20/20) | 46.81 s
@@ -690,8 +690,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621105
- class='n02123159 tiger cat' with probability=0.356377
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 415.61734948000776, 'median': 415.4157348999888, 'std': 1.2347701512066156}
- unoptimized: {'mean': 496.1427404700089, 'median': 496.0948851000012, 'std': 0.6810259431842657}
+ optimized: {'mean': 411.3008441899956, 'median': 410.90171700000155, 'std': 0.9522105819474678}
+ unoptimized: {'mean': 493.6193124900001, 'median': 493.7237737500027, 'std': 0.820370130637166}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 32.700 seconds)
+ **Total running time of the script:** ( 10 minutes 25.791 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 4a046b964..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
- 1.213e-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 e5f8c89d9..5df80ae97 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, 0x1b54f660)), stage(b, placeholder(b, 0x1b5709a0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x1b179bd0)), stage(b, placeholder(b, 0x1b21b050)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 208bf39af..18467e1e9 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**13:36.209** total execution time for **tutorial** files:
+**13:22.702** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:32.700 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:25.791 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:05.533 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.946 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.941 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:57.459 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.409 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.934 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.250 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.904 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.700 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.816 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.520 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.700 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.146 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.143 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :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 9a0dd49ec..957004301 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: 0.000007
- naive: 0.000007
+ Numpy running time: 0.000008
+ naive: 0.000006
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.000028
+ vector: 0.000025
@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 6.7660700005944815e-06 1.0
- naive 6.6816000000000005e-06 0.987515647844752
- parallel 6.9194e-06 1.0226616040614487
- vector 2.7578599999999997e-05 4.07601458417913
+ numpy 8.43765000354324e-06 1.0
+ naive 5.8182e-06 0.6895521854493551
+ parallel 7.0312e-06 0.8333125926113757
+ vector 2.4595500000000002e-05 2.9149703993021236
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019008
+ Numpy running time: 0.018101
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: 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: 3.393141
+ none: 3.417285
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.311018
+ blocking: 0.305122
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.333327
+ vectorization: 0.336167
@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:267: 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: 0.119382
+ loop permutation: 0.116110
@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:267: 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: 0.110051
+ array packing: 0.108080
@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:267: 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: 0.110626
+ block caching: 0.110487
@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:267: 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: 0.146517
+ parallelization: 0.145963
@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 3.3931412672 1.0
- blocking 0.311018449 0.09166091963410959
- vectorization 0.3333269217 0.09823549786215044
- loop permutation 0.11938214259999999 0.035183369391075615
- array packing 0.11005143619999999 0.032433496731721335
- block caching 0.1106260794 0.03260285107177043
- parallelization 0.1465170597 0.04318035948468041
+ none 3.4172851178999997 1.0
+ blocking 0.30512232399999994 0.08928793281009711
+ vectorization 0.33616703130000003 0.09837254419864808
+ loop permutation 0.11610994780000002 0.033977249130254676
+ array packing 0.10808032809999998 0.03162754185592153
+ block caching 0.1104865881 0.03233168561828887
+ parallelization 0.1459627158 0.04271306337169122
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.941 seconds)
+ **Total running time of the script:** ( 1 minutes 0.946 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index b4f71691e..56124e665 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-32f9a5f4d4f03a0875d64ac42df46cafe8ae3cfa
+e814f798edc5bf6977a4f4f74ec8d1d7e363c608
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index bb09c2da0..5cc550d75 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.914 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.087 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 3cf585574..1cfa89bec 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip8841a18d-8118-4067-83d4-f7df722b6563 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.zip2f230d7a-e57a-473a-8ce9-6ee9b2886e82 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 63bca5241..66c419b66 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,14 +432,14 @@ 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]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 43.3MB/s]
- 25%|##5 | 10.5M/41.5M [00:00<00:00, 35.4MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 35.6MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 40.1MB/s]
- 63%|######3 | 26.2M/41.5M [00:00<00:00, 38.5MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 36.3MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 30.9MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 34.8MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 43.1MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 39.7MB/s]
+ 44%|####3 | 18.1M/41.5M [00:00<00:00, 31.1MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 29.0MB/s]
+ 60%|###### | 25.1M/41.5M [00:00<00:00, 25.2MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:01<00:00, 29.2MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 33.7MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 32.6MB/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 a0fb9ed2f..ff4369986 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,8 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 41%|####1 | 18.5M/44.7M [00:00<00:00, 194MB/s]
- 98%|#########8| 44.0M/44.7M [00:00<00:00, 237MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 231MB/s]
+ 44%|####3 | 19.6M/44.7M [00:00<00:00, 206MB/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 f904067f3..863149054 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.252 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.811 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 bd5fe2e63..bf3f88630 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:17.954</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:08.244</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:06.252</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:05.087</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>01:05.914</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:02.811</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>00:41.435</p></td>
+<td><p>00:39.585</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>00:29.830</p></td>
+<td><p>00:29.057</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:26.748</p></td>
+<td><p>00:26.392</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:25.729</p></td>
+<td><p>00:24.901</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.778</p></td>
+<td><p>00:22.296</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:20.474</p></td>
+<td><p>00:19.663</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>00:16.313</p></td>
+<td><p>00:16.043</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>00:02.482</p></td>
+<td><p>00:02.409</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 c9fc3a58e..f859f55f6 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2969 16.2793 16.7325 15.9991 0.1869
+ 16.2342 16.0242 16.9421 15.7300 0.4926
</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 6feed8c93..fcd6b99e6 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,17 +436,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|1 | 3.30M/170M [00:00<00:05, 34.5MB/s]
- 4%|3 | 6.59M/170M [00:00<00:05, 32.7MB/s]
- 13%|#2 | 21.9M/170M [00:00<00:01, 89.5MB/s]
- 23%|##3 | 39.4M/170M [00:00<00:01, 123MB/s]
- 33%|###2 | 55.8M/170M [00:00<00:00, 140MB/s]
- 45%|####4 | 76.2M/170M [00:00<00:00, 165MB/s]
- 58%|#####8 | 99.3M/170M [00:00<00:00, 190MB/s]
- 72%|#######2 | 123M/170M [00:00<00:00, 205MB/s]
- 84%|########3 | 142M/170M [00:00<00:00, 201MB/s]
- 95%|#########5| 162M/170M [00:01<00:00, 203MB/s]
-100%|##########| 170M/170M [00:01<00:00, 169MB/s]
+ 10%|# | 17.4M/170M [00:00<00:00, 182MB/s]
+ 25%|##4 | 42.0M/170M [00:00<00:00, 227MB/s]
+ 40%|###9 | 67.6M/170M [00:00<00:00, 246MB/s]
+ 55%|#####4 | 93.2M/170M [00:00<00:00, 255MB/s]
+ 70%|####### | 120M/170M [00:00<00:00, 262MB/s]
+ 85%|########5 | 145M/170M [00:00<00:00, 254MB/s]
+ 99%|#########9| 169M/170M [00:00<00:00, 252MB/s]
+100%|##########| 170M/170M [00:00<00:00, 248MB/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').
@@ -541,7 +538,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 1.461 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 57.369 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 02639d5e1..37aab0ed8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 181MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 202MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +569,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3182 90.2006 93.1299 90.0170 0.3694
+ 90.1958 90.0433 95.9251 89.9258 0.6247
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.732 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.184 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 79e8f2aa9..eb81f7d4a 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.3434 120.2225 122.8440 119.3696 0.4921
+ 120.3033 120.2422 123.1208 119.4754 0.4228
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 58.651 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 58.694 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 a336ba138..812f2d455 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.319 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 35.506 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 8d3a82d34..38cea42a2 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,23 +441,26 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6435/132723 [00:00<00:01, 64342.39KB/s]
- 11%|#1 | 14873/132723 [00:00<00:01, 76121.11KB/s]
- 17%|#7 | 23210/132723 [00:00<00:01, 79425.86KB/s]
- 24%|##3 | 31697/132723 [00:00<00:01, 81566.85KB/s]
- 30%|### | 39854/132723 [00:00<00:01, 79727.16KB/s]
- 36%|###6 | 48402/132723 [00:00<00:01, 81643.15KB/s]
- 43%|####2 | 56574/132723 [00:00<00:01, 70251.76KB/s]
- 49%|####9 | 65042/132723 [00:00<00:00, 74353.66KB/s]
- 55%|#####5 | 73560/132723 [00:00<00:00, 77476.16KB/s]
- 62%|######1 | 81905/132723 [00:01<00:00, 71207.20KB/s]
- 67%|######7 | 89244/132723 [00:01<00:00, 70829.89KB/s]
- 74%|#######3 | 97749/132723 [00:01<00:00, 74775.05KB/s]
- 79%|#######9 | 105368/132723 [00:01<00:00, 46321.47KB/s]
- 84%|########3 | 111402/132723 [00:01<00:00, 48097.81KB/s]
- 89%|########9 | 118405/132723 [00:01<00:00, 52891.20KB/s]
- 96%|#########5| 126837/132723 [00:01<00:00, 60368.72KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 66310.61KB/s]
+ 4%|3 | 5133/132723 [00:00<00:02, 51322.83KB/s]
+ 9%|9 | 12605/132723 [00:00<00:01, 65083.75KB/s]
+ 14%|#4 | 19114/132723 [00:00<00:01, 63525.31KB/s]
+ 20%|## | 26736/132723 [00:00<00:01, 68461.76KB/s]
+ 25%|##5 | 33593/132723 [00:00<00:01, 55569.31KB/s]
+ 31%|### | 41123/132723 [00:00<00:01, 61343.57KB/s]
+ 36%|###6 | 47927/132723 [00:00<00:01, 45994.32KB/s]
+ 40%|#### | 53240/132723 [00:01<00:02, 39424.71KB/s]
+ 46%|####5 | 60841/132723 [00:01<00:01, 47356.51KB/s]
+ 50%|##### | 66769/132723 [00:01<00:01, 50175.40KB/s]
+ 56%|#####5 | 74236/132723 [00:01<00:01, 56359.29KB/s]
+ 61%|###### | 80692/132723 [00:01<00:00, 58130.74KB/s]
+ 65%|######5 | 86909/132723 [00:01<00:01, 43419.40KB/s]
+ 71%|#######1 | 94605/132723 [00:01<00:00, 50881.44KB/s]
+ 77%|#######6 | 102175/132723 [00:01<00:00, 56866.33KB/s]
+ 83%|########2 | 109789/132723 [00:02<00:00, 61804.67KB/s]
+ 88%|########7 | 116563/132723 [00:02<00:00, 51216.28KB/s]
+ 94%|#########3| 124232/132723 [00:02<00:00, 57232.19KB/s]
+ 99%|#########9| 131945/132723 [00:02<00:00, 62248.31KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 54759.09KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -500,7 +503,7 @@ 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 41.547 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 36.713 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 00dc72661..de7e6e810 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:50.738</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:32.050</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,39 +336,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:01.461</p></td>
+<td><p>02:57.369</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>02:41.547</p></td>
+<td><p>02:36.713</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>01:58.651</p></td>
+<td><p>01:58.694</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>01:41.319</p></td>
+<td><p>01:35.506</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:10.732</p></td>
+<td><p>01:09.184</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>00:30.971</p></td>
+<td><p>00:29.424</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:23.368</p></td>
+<td><p>00:22.751</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.683</p></td>
+<td><p>00:22.403</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 61164b91b..c9b5e4c38 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb246fdbf-5d17-4a13-8cdf-96bc3ea3de28 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.zip94d9fc72-cd61-45df-a050-a95a82ee200e 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 fcc1143bd..8b936ff72 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:42.137</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:41.701</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:38.932</p></td>
+<td><p>00:38.547</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>00:02.244</p></td>
+<td><p>00:02.200</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.952</p></td>
+<td><p>00:00.945</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index ff471a0f7..324760013 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6896us [6896us] (46.62%; 46.62%)
-FoldScaleAxis: 7896us [6us] (53.38%; 53.38%)
- FoldConstant: 7891us [1596us] (53.35%; 99.93%)
- InferType: 6295us [6295us] (42.56%; 79.77%)
+InferType: 7066us [7066us] (46.47%; 46.47%)
+FoldScaleAxis: 8140us [6us] (53.53%; 53.53%)
+ FoldConstant: 8133us [1733us] (53.49%; 99.92%)
+ InferType: 6400us [6400us] (42.09%; 78.69%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6268us [6268us] (44.69%; 44.69%)
-FoldScaleAxis: 7757us [4us] (55.31%; 55.31%)
- FoldConstant: 7753us [1587us] (55.28%; 99.95%)
- InferType: 6165us [6165us] (43.96%; 79.52%)
+InferType: 6509us [6509us] (44.86%; 44.86%)
+FoldScaleAxis: 8000us [5us] (55.14%; 55.14%)
+ FoldConstant: 7995us [1695us] (55.10%; 99.93%)
+ InferType: 6300us [6300us] (43.42%; 78.80%)
</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 a6da83d44..10fe7f05c 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 48.049035 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 42.838868 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 46322d1c1..07029a274 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.209077 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.173363 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 cfce1e1d9..03f70884f 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018978
-Baseline: 3.401331
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018693
+Baseline: 3.413802
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.318578
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.304378
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.340245
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336063
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.126273
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116909
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109408
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109347
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110941
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111617
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147097
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146532
</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 a9c174eac..41c985216 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.895</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.714</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.693</p></td>
+<td><p>00:32.352</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>00:01.249</p></td>
+<td><p>00:01.305</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>00:00.954</p></td>
+<td><p>00:01.057</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 81a519d92..b4001bf47 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:18.178</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:04.930</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:26.380</p></td>
+<td><p>03:18.336</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>01:24.106</p></td>
+<td><p>01:22.648</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>00:48.174</p></td>
+<td><p>00:47.079</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>00:21.564</p></td>
+<td><p>00:19.314</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:09.107</p></td>
+<td><p>00:08.791</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>00:08.846</p></td>
+<td><p>00:08.763</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 06cacc147..37e5009ba 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,215 +491,439 @@ 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" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [392]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [128]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[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
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- let cse_var_2: int32 = (rc.outer.outer*1568)
- let cse_var_1: int32 = (rc.outer.outer*288)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 21), 81)) && (floormod((threadIdx.x_1 + 21), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (floormod((threadIdx.x_1 + 8), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 7), 9)) && (floormod((threadIdx.x_1 + 63), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1764), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 7), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 16), 81)) && (floormod((threadIdx.x_1 + 16), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 50), 81)) && (floormod((threadIdx.x_1 + 50), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 50), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (floormod((threadIdx.x_1 + 3), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[(threadIdx.x_2*3)] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 2)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 588)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 4), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 589)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 4), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 590)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 4), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 1176)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1177)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 1178)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 1764)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 12), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1765)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 12), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 1766)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 12), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 2352)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 2353)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 2354)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 2940)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 20), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 2941)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 20), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 2942)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 20), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 3528)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 3529)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 3530)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 4116)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 4117)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 4118)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 4704)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 4705)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 4706)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 5292)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1764), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 36), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 5293)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1764), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 36), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 5294)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1764), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 36), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 5880)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 5881)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 5882)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 6468)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2156), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 44), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 6469)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2156), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 44), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 6470)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2156), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 44), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 7056)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 7057)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 7058)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 7644)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2548), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 52), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 7645)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2548), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 52), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 7646)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2548), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 52), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- kernel.shared_1[((threadIdx.x_2*3) + 8232)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 56), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 8233)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 56), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 8234)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 56), 96)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_2 < 132), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*3) + 8820)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2940), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 60), 96)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 8821)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2940), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 60), 96)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 8822)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2940), 96)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 60), 96)*3)) + 2)]
- }
- for (rc.outer.inner: int32, 0, 32) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2304)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4608)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6912)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2305)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4609)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6913)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2306)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4610)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6914)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 288)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2592)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4896)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7200)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 289)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2593)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4897)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7201)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 290)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2594)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4898)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7202)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2307)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4611)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6915)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2308)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4612)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6916)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2309)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4613)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6917)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 291)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2595)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4899)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7203)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 292)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2596)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4900)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7204)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 293)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2597)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4901)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7205)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2310)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4614)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6918)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2311)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4615)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6919)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2312)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4616)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 6920)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 294)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2598)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4902)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7206)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 295)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2599)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4903)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7207)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 296)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 2600)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 4904)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*9)) + 7208)]))
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (ry.outer.outer*7)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [392], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [128], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64512)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)), data[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32257)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64513)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 49), 7) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((cse_var_2 + cse_var_1) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 1), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 2), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 3), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 4), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 5), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7))) && ((ry.outer.outer + floormod((floordiv(threadIdx.x_1, 7) + 6), 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 49)*49)) + cse_var_1) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 32258)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 8)*4608)) + (rc.outer.outer*72)) + (floormod(threadIdx.x_2, 8)*9)) + (ry.outer.outer*3)) + 64514)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 50)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 51)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 52)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 53)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 295)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 296)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 300)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*16) + 15)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 16)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1176)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 24)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -736,7 +960,7 @@ 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: 0.409 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.254 ms
</pre></div>
</div>
</div>
@@ -767,34 +991,34 @@ 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=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
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_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_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=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+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=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)
@@ -812,14 +1036,14 @@ 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=3)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=196)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -839,167 +1063,410 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[9216];
+extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[392];
+ __shared__ float kernel_shared[128];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((9 <= ((((int)threadIdx.x) + 21) % 81)) && (((((int)threadIdx.x) + 21) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((9 <= ((((int)threadIdx.x) + 8) % 81)) && (((((int)threadIdx.x) + 8) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 81) * 49)) + ((((((int)threadIdx.x) + 8) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) / 9) + 7) % 9)) && (((((int)threadIdx.x) + 63) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1764) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 7) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((9 <= ((((int)threadIdx.x) + 16) % 81)) && (((((int)threadIdx.x) + 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + ((((((int)threadIdx.x) + 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((9 <= ((((int)threadIdx.x) + 50) % 81)) && (((((int)threadIdx.x) + 50) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2156) / 81) * 49)) + ((((((int)threadIdx.x) + 50) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((9 <= ((((int)threadIdx.x) + 3) % 81)) && (((((int)threadIdx.x) + 3) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + ((((((int)threadIdx.x) + 3) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 44) {
- pad_temp_shared[(((int)threadIdx.x) + 2548)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2548) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 3)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 588)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 589)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 590)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 4) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1176)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1177)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1178)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1764)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 12) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1765)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 12) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1766)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 12) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2352)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 2353)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2354)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2940)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 20) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 2941)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 20) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2942)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 20) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 3528)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 24) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 3529)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 24) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 3530)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 24) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 4116)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 28) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 4117)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 28) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 4118)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 28) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 4704)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 4705)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 4706)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 5292)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 36) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 5293)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 36) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 5294)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 36) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 5880)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 5881)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 5882)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 6468)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 44) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 6469)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 44) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 6470)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 44) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 7056)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 48) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 7057)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 48) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 7058)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 48) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 7644)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 52) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 7645)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 52) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 7646)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 52) % 96) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 8232)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 8233)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 8234)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) % 96) * 3)) + 2)];
- if (((int)threadIdx.x) < 132) {
- kernel_shared[((((int)threadIdx.x) * 3) + 8820)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 60) % 96) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 8821)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 60) % 96) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 8822)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 60) % 96) * 3)) + 2)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2304)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4608)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6912)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2305)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4609)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6913)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2306)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4610)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6914)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 288)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2592)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4896)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7200)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 289)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2593)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4897)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 290)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2594)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4898)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7202)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2307)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4611)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6915)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2308)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4612)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6916)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2309)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4613)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6917)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 291)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2595)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4899)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7203)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 292)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2596)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4900)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7204)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 293)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2597)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4901)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7205)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2310)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4614)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6918)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2311)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4615)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6919)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2312)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4616)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 6920)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 294)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2598)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4902)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7206)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 295)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2599)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4903)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7207)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 296)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 2600)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 4904)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 9)) + 7208)]));
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32256)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64512)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32257)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64513)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 1) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 1) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 2) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 2) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 3) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 3) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 4) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 4) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 5) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 5) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = ((((1 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + 6) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 49) * 49)) + (ry_outer_outer * 7)) + ((((((int)threadIdx.x) / 7) + 6) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 32258)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 3) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) & 7) * 9)) + (ry_outer_outer * 3)) + 64514)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 49)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 50)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 51)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 52)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 53)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 294)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 295)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 296)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 300)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 16) + 15)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1176)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 24)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -1036,7 +1503,7 @@ 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 26.380 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 18.336 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 51325fbf1..576d31b89 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.9503 9.9650 9.9681 9.9179 0.0230
+ 9.8647 9.8428 9.9172 9.8341 0.0373
</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 6984eb426..3daee158f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 756.0070 756.2754 756.3648 755.3809 0.4443
+ 753.4929 753.2963 753.9879 753.1944 0.3525
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.106 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.648 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 2714da694..d80d4c07a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,31 +625,29 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), 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_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [256], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
- }
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global;
+ for (i1.outer: int32, 0, 32) {
+ for (i.outer.inner: int32, 0, 16) {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
+ for (i.inner: int32, 0, 8) {
+ for (j: int32, 0, 16) {
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ let cse_var_1: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
- }
+ }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_2: int32 = ((i0.inner*512) + (i1.outer*16))
+ compute[ramp(cse_var_2, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -686,7 +684,7 @@ 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: 1.572 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.520 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 ff5e5feb6..0ae451814 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.422</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.411</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,7 +336,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.385</p></td>
+<td><p>00:46.375</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>
@@ -347,11 +347,11 @@
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index add155764..1ab95698e 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 201.90/201.90 result: MeasureResult(costs=(0.0011465961666666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1001603603363037, timestamp=1662046198.3345554) [('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: 0.00/201.90 result: Traceback (most recent call last):
+No: 9 GFLOPS: 80.75/80.75 result: MeasureResult(costs=(0.0028669616285714283,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8190627098083496, timestamp=1662054114.377857) [('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: 0.00/80.75 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.26/260.26 result: MeasureResult(costs=(0.0008895155248618784,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7303051948547363, timestamp=1662046199.2413735) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.72/260.72 result: MeasureResult(costs=(0.0008879196906077348,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.69096040725708, timestamp=1662054115.253785) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.30/260.26 result: MeasureResult(costs=(0.043684947,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8386874198913574, timestamp=1662046203.8067925) [('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: 3.35/260.26 result: MeasureResult(costs=(0.069142329,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.547529935836792, timestamp=1662046205.0482953) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.27/260.72 result: MeasureResult(costs=(0.043939778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8757946491241455, timestamp=1662054119.8422925) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.36/260.72 result: MeasureResult(costs=(0.0689503045,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5667665004730225, timestamp=1662054121.0828333) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.26 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: 28.06/260.26 result: MeasureResult(costs=(0.008248774928571428,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.29433274269104, timestamp=1662046216.103824) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+No: 18 GFLOPS: 28.03/260.72 result: MeasureResult(costs=(0.008257903214285715,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2839818000793457, timestamp=1662054132.120746) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.26 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.72 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001269
+Time cost of this operator: 0.001273
</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 9aa5422e3..7c8a48ac8 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.5 98.739 (1, 2, 10, 10, 3) 2 1 [314.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.033 0.952 (1, 6, 10, 10) 1 1 [3.033]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.983 0.309 (1, 1, 10, 10, 3) 1 1 [0.983]
-Total_time - 318.516 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.1 98.738 (1, 2, 10, 10, 3) 2 1 [311.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.958 (1, 6, 10, 10) 1 1 [3.017]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 0.304 (1, 1, 10, 10, 3) 1 1 [0.957]
+Total_time - 315.075 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 289.7 98.635 (1, 2, 10, 10, 3) 2 1 [289.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.036 1.034 (1, 6, 10, 10) 1 1 [3.036]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.331 (1, 1, 10, 10, 3) 1 1 [0.972]
-Total_time - 293.709 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.812 96.675 (1, 6, 10, 10, 1) 2 1 [79.812]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.767 2.14 (1, 6, 10, 10) 1 1 [1.767]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 1.185 (1, 1, 10, 10, 3) 1 1 [0.978]
+Total_time - 82.558 - - - - -
</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 75a462c8e..a563a1536 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpkbf_xhfy/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp_mmaw2it/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpkbf_xhfy/images/target contains 8144 images
-/tmp/tmpkbf_xhfy/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/tmp_mmaw2it/images/target contains 8144 images
+/tmp/tmp_mmaw2it/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 56s - loss: 0.2021 - accuracy: 0.9264 - val_loss: 0.1240 - val_accuracy: 0.9577
+328/328 - 56s - loss: 0.2197 - accuracy: 0.9250 - val_loss: 0.1481 - val_accuracy: 0.9558
Epoch 2/3
-328/328 - 53s - loss: 0.0972 - accuracy: 0.9633 - val_loss: 0.1237 - val_accuracy: 0.9577
+328/328 - 52s - loss: 0.1012 - accuracy: 0.9616 - val_loss: 0.1194 - val_accuracy: 0.9596
Epoch 3/3
-328/328 - 53s - loss: 0.0665 - accuracy: 0.9754 - val_loss: 0.1077 - val_accuracy: 0.9671
+328/328 - 52s - loss: 0.0672 - accuracy: 0.9751 - val_loss: 0.1141 - val_accuracy: 0.9630
-<keras.callbacks.History object at 0x7f1490619bd0>
+<keras.callbacks.History object at 0x7f11784f4f10>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 10.483 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 10.137 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 7e67be0de..559b365e7 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:04.849</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:03.680</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:10.483</p></td>
+<td><p>05:10.137</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>00:43.129</p></td>
+<td><p>00:42.128</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.852</p></td>
+<td><p>00:08.122</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.382</p></td>
+<td><p>00:03.291</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index ac1077831..e487d5b1c 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.407</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.040</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.748</p></td>
+<td><p>00:31.558</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.317</p></td>
+<td><p>00:09.910</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>00:01.335</p></td>
+<td><p>00:01.565</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 33b151061..03e03725b 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f1491d35830>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f10f6f329e0>
</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 9413208b7..baf793ce5 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.144</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.173</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,7 +336,7 @@
</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>00:01.920</p></td>
+<td><p>00:01.939</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>
@@ -344,19 +344,19 @@
<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>00:00.536</p></td>
+<td><p>00:00.540</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>00:00.519</p></td>
+<td><p>00:00.528</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>00:00.103</p></td>
+<td><p>00:00.100</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.044</p></td>
+<td><p>00:00.041</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index e7e71738d..e2d92d646 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpe5wr_w3p/input0.cc'\nsource_filename = \"/tmp/tmpe5wr_w3p/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/tmpl0dhmv6r/input0.cc'\nsource_filename = \"/tmp/tmpl0dhmv6r/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/classtvm_1_1runtime_1_1ModuleNode.html b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1ModuleNode.html
index 4f35ff390..caeb31e49 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1ModuleNode.html
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1ModuleNode.html
@@ -80,7 +80,7 @@ $(function() {
<div class="dynheader">
Inheritance diagram for tvm::runtime::ModuleNode:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1runtime_1_1ModuleNode__inherit__graph.svg" width="488" height="1395"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1runtime_1_1ModuleNode__inherit__graph.svg" width="494" height="1395"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<div class="dynheader">
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1ModuleNode__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1ModuleNode__inherit__graph.svg
index 95cd16809..4ceacbf56 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1ModuleNode__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1ModuleNode__inherit__graph.svg
@@ -4,43 +4,43 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::runtime::ModuleNode Pages: 1 -->
-<svg width="366pt" height="1046pt"
- viewBox="0.00 0.00 366.00 1046.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<svg width="370pt" height="1046pt"
+ viewBox="0.00 0.00 369.50 1046.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1042)">
<title>tvm::runtime::ModuleNode</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1042 362,-1042 362,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1042 365.5,-1042 365.5,4 -4,4"/>
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="89.5,-380.5 89.5,-602.5 298.5,-602.5 298.5,-380.5 89.5,-380.5"/>
-<text text-anchor="middle" x="194" y="-590.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ModuleNode</text>
-<polyline fill="none" stroke="#000000" points="89.5,-583.5 298.5,-583.5 "/>
-<text text-anchor="start" x="97.5" y="-571.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="97.5" y="-560.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="97.5" y="-549.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># imports_</text>
-<polyline fill="none" stroke="#000000" points="89.5,-542.5 298.5,-542.5 "/>
-<text text-anchor="start" x="97.5" y="-530.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ModuleNode()</text>
-<text text-anchor="start" x="97.5" y="-519.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
-<text text-anchor="start" x="97.5" y="-508.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="97.5" y="-497.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
-<text text-anchor="start" x="97.5" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
-<text text-anchor="start" x="97.5" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetSource()</text>
-<text text-anchor="start" x="97.5" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFormat()</text>
-<text text-anchor="start" x="97.5" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="97.5" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Import()</text>
-<text text-anchor="start" x="97.5" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFuncFromEnv()</text>
-<text text-anchor="start" x="97.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ imports()</text>
-<text text-anchor="start" x="97.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsDSOExportable()</text>
-<text text-anchor="start" x="97.5" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ImplementsFunction()</text>
-<text text-anchor="start" x="97.5" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="92,-380.5 92,-602.5 301,-602.5 301,-380.5 92,-380.5"/>
+<text text-anchor="middle" x="196.5" y="-590.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ModuleNode</text>
+<polyline fill="none" stroke="#000000" points="92,-583.5 301,-583.5 "/>
+<text text-anchor="start" x="100" y="-571.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="100" y="-560.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="100" y="-549.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># imports_</text>
+<polyline fill="none" stroke="#000000" points="92,-542.5 301,-542.5 "/>
+<text text-anchor="start" x="100" y="-530.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ModuleNode()</text>
+<text text-anchor="start" x="100" y="-519.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
+<text text-anchor="start" x="100" y="-508.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="100" y="-497.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
+<text text-anchor="start" x="100" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
+<text text-anchor="start" x="100" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetSource()</text>
+<text text-anchor="start" x="100" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFormat()</text>
+<text text-anchor="start" x="100" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="100" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Import()</text>
+<text text-anchor="start" x="100" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFuncFromEnv()</text>
+<text text-anchor="start" x="100" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ imports()</text>
+<text text-anchor="start" x="100" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsDSOExportable()</text>
+<text text-anchor="start" x="100" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ImplementsFunction()</text>
+<text text-anchor="start" x="100" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
</g>
<!-- Node2 -->
<g id="node3" class="node">
<title>Node2</title>
<g id="a_node3"><a xlink:href="classtvm_1_1runtime_1_1vm_1_1Executable.html" target="_top" xlink:title="The executable emitted by the VM compiler. ">
-<polygon fill="#ffffff" stroke="#000000" points="0,-22.5 0,-321.5 200,-321.5 200,-22.5 0,-22.5"/>
-<text text-anchor="middle" x="100" y="-309.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Executable</text>
-<polyline fill="none" stroke="#000000" points="0,-302.5 200,-302.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="0,-22.5 0,-321.5 203,-321.5 203,-22.5 0,-22.5"/>
+<text text-anchor="middle" x="101.5" y="-309.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Executable</text>
+<polyline fill="none" stroke="#000000" points="0,-302.5 203,-302.5 "/>
<text text-anchor="start" x="8" y="-290.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ virtual_devices</text>
<text text-anchor="start" x="8" y="-279.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ host_device_index</text>
<text text-anchor="start" x="8" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ constants</text>
@@ -51,7 +51,7 @@
<text text-anchor="start" x="8" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ op_attrs</text>
<text text-anchor="start" x="8" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ functions</text>
<text text-anchor="start" x="8" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ const_device_indexes</text>
-<polyline fill="none" stroke="#000000" points="0,-184.5 200,-184.5 "/>
+<polyline fill="none" stroke="#000000" points="0,-184.5 203,-184.5 "/>
<text text-anchor="start" x="8" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
<text text-anchor="start" x="8" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
<text text-anchor="start" x="8" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
@@ -59,12 +59,12 @@
<text text-anchor="start" x="8" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsTo</text>
<text text-anchor="start" x="8" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsToFile()</text>
-<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFrom</text>
-<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
-<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromFile()</text>
-<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetBytecode()</text>
-<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetConstants()</text>
-<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 10 more...</text>
+<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetLateBoundConstants()</text>
+<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFrom</text>
+<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
+<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromMap()</text>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromFile()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Load()</text>
</a>
</g>
@@ -72,103 +72,103 @@
<!-- Node0->Node2 -->
<g id="edge2" class="edge">
<title>Node0->Node2</title>
-<path fill="none" stroke="#191970" d="M158.3624,-370.3701C153.6801,-354.4551 148.8377,-337.9962 144.0367,-321.678"/>
-<polygon fill="none" stroke="#191970" points="155.0751,-371.5974 161.2553,-380.2029 161.7905,-369.6216 155.0751,-371.5974"/>
+<path fill="none" stroke="#191970" d="M160.4833,-370.3701C155.7511,-354.4551 150.8573,-337.9962 146.0052,-321.678"/>
+<polygon fill="none" stroke="#191970" points="157.202,-371.6152 163.407,-380.2029 163.9117,-369.6201 157.202,-371.6152"/>
</g>
<!-- Node3 -->
<g id="node4" class="node">
<title>Node3</title>
<g id="a_node4"><a xlink:href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html" target="_top" xlink:title="The virtual machine. ">
-<polygon fill="#ffffff" stroke="#000000" points="218,-.5 218,-343.5 358,-343.5 358,-.5 218,-.5"/>
-<text text-anchor="start" x="226" y="-331.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Virtual</text>
-<text text-anchor="middle" x="288" y="-320.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Machine</text>
-<polyline fill="none" stroke="#000000" points="218,-313.5 358,-313.5 "/>
-<text text-anchor="start" x="226" y="-301.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># packed_funcs_</text>
-<text text-anchor="start" x="226" y="-290.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># frames_</text>
-<text text-anchor="start" x="226" y="-279.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># func_index_</text>
-<text text-anchor="start" x="226" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># code_</text>
-<text text-anchor="start" x="226" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># pc_</text>
-<text text-anchor="start" x="226" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># return_register_</text>
-<text text-anchor="start" x="226" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># exec_</text>
-<text text-anchor="start" x="226" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># inputs_</text>
-<text text-anchor="start" x="226" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># devices_</text>
-<text text-anchor="start" x="226" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># allocators_</text>
-<text text-anchor="start" x="226" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># const_pool_</text>
-<polyline fill="none" stroke="#000000" points="218,-184.5 358,-184.5 "/>
-<text text-anchor="start" x="226" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="226" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~VirtualMachine()</text>
-<text text-anchor="start" x="226" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
-<text text-anchor="start" x="226" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VirtualMachine()</text>
-<text text-anchor="start" x="226" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadExecutable()</text>
-<text text-anchor="start" x="226" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PushFrame()</text>
-<text text-anchor="start" x="226" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PopFrame()</text>
-<text text-anchor="start" x="226" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># WriteRegister()</text>
-<text text-anchor="start" x="226" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ReadRegister()</text>
-<text text-anchor="start" x="226" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># LoadScalarInt()</text>
-<text text-anchor="start" x="226" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
-<text text-anchor="start" x="226" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
-<text text-anchor="start" x="226" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># InvokePacked()</text>
-<text text-anchor="start" x="226" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Init()</text>
-<text text-anchor="start" x="226" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># RunLoop()</text>
-<text text-anchor="start" x="226" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 7 more...</text>
+<polygon fill="#ffffff" stroke="#000000" points="221.5,-.5 221.5,-343.5 361.5,-343.5 361.5,-.5 221.5,-.5"/>
+<text text-anchor="start" x="229.5" y="-331.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Virtual</text>
+<text text-anchor="middle" x="291.5" y="-320.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Machine</text>
+<polyline fill="none" stroke="#000000" points="221.5,-313.5 361.5,-313.5 "/>
+<text text-anchor="start" x="229.5" y="-301.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># packed_funcs_</text>
+<text text-anchor="start" x="229.5" y="-290.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># frames_</text>
+<text text-anchor="start" x="229.5" y="-279.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># func_index_</text>
+<text text-anchor="start" x="229.5" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># code_</text>
+<text text-anchor="start" x="229.5" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># pc_</text>
+<text text-anchor="start" x="229.5" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># return_register_</text>
+<text text-anchor="start" x="229.5" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># exec_</text>
+<text text-anchor="start" x="229.5" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># inputs_</text>
+<text text-anchor="start" x="229.5" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># devices_</text>
+<text text-anchor="start" x="229.5" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># allocators_</text>
+<text text-anchor="start" x="229.5" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># const_pool_</text>
+<polyline fill="none" stroke="#000000" points="221.5,-184.5 361.5,-184.5 "/>
+<text text-anchor="start" x="229.5" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="229.5" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~VirtualMachine()</text>
+<text text-anchor="start" x="229.5" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
+<text text-anchor="start" x="229.5" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VirtualMachine()</text>
+<text text-anchor="start" x="229.5" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadExecutable()</text>
+<text text-anchor="start" x="229.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PushFrame()</text>
+<text text-anchor="start" x="229.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PopFrame()</text>
+<text text-anchor="start" x="229.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># WriteRegister()</text>
+<text text-anchor="start" x="229.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ReadRegister()</text>
+<text text-anchor="start" x="229.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># LoadScalarInt()</text>
+<text text-anchor="start" x="229.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="229.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="229.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># InvokePacked()</text>
+<text text-anchor="start" x="229.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Init()</text>
+<text text-anchor="start" x="229.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># RunLoop()</text>
+<text text-anchor="start" x="229.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 7 more...</text>
</a>
</g>
</g>
<!-- Node0->Node3 -->
<g id="edge3" class="edge">
<title>Node0->Node3</title>
-<path fill="none" stroke="#191970" d="M229.6376,-370.3701C232.2198,-361.5933 234.8507,-352.651 237.4965,-343.6582"/>
-<polygon fill="none" stroke="#191970" points="226.2095,-369.6216 226.7447,-380.2029 232.9249,-371.5974 226.2095,-369.6216"/>
+<path fill="none" stroke="#191970" d="M232.5167,-370.3701C235.1264,-361.5933 237.7853,-352.651 240.4592,-343.6582"/>
+<polygon fill="none" stroke="#191970" points="229.0883,-369.6201 229.593,-380.2029 235.798,-371.6152 229.0883,-369.6201"/>
</g>
<!-- Node1 -->
<g id="node2" class="node">
<title>Node1</title>
<g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1Object.html" target="_top" xlink:title="base class of all object containers. ">
-<polygon fill="#ffffff" stroke="#000000" points="102.5,-639.5 102.5,-1037.5 285.5,-1037.5 285.5,-639.5 102.5,-639.5"/>
-<text text-anchor="middle" x="194" y="-1025.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
-<polyline fill="none" stroke="#000000" points="102.5,-1018.5 285.5,-1018.5 "/>
-<text text-anchor="start" x="110.5" y="-1006.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="110.5" y="-995.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
-<text text-anchor="start" x="110.5" y="-984.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
-<text text-anchor="start" x="110.5" y="-973.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
-<text text-anchor="start" x="110.5" y="-962.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
-<text text-anchor="start" x="110.5" y="-951.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
-<text text-anchor="start" x="110.5" y="-940.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
-<text text-anchor="start" x="110.5" y="-929.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="110.5" y="-918.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="110.5" y="-907.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
-<text text-anchor="start" x="110.5" y="-896.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="110.5" y="-885.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="110.5" y="-874.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
-<text text-anchor="start" x="110.5" y="-863.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
-<text text-anchor="start" x="110.5" y="-852.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
-<polyline fill="none" stroke="#000000" points="102.5,-845.5 285.5,-845.5 "/>
-<text text-anchor="start" x="110.5" y="-833.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
-<text text-anchor="start" x="110.5" y="-822.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
-<text text-anchor="start" x="110.5" y="-811.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
-<text text-anchor="start" x="110.5" y="-800.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
-<text text-anchor="start" x="110.5" y="-789.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="110.5" y="-778.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="110.5" y="-767.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="110.5" y="-756.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="110.5" y="-745.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="110.5" y="-734.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="110.5" y="-723.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
-<text text-anchor="start" x="110.5" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
-<text text-anchor="start" x="110.5" y="-701.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
-<text text-anchor="start" x="110.5" y="-690.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
-<text text-anchor="start" x="110.5" y="-679.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
-<text text-anchor="start" x="110.5" y="-668.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
-<text text-anchor="start" x="110.5" y="-657.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
-<text text-anchor="start" x="110.5" y="-646.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
+<polygon fill="#ffffff" stroke="#000000" points="105,-639.5 105,-1037.5 288,-1037.5 288,-639.5 105,-639.5"/>
+<text text-anchor="middle" x="196.5" y="-1025.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
+<polyline fill="none" stroke="#000000" points="105,-1018.5 288,-1018.5 "/>
+<text text-anchor="start" x="113" y="-1006.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="113" y="-995.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
+<text text-anchor="start" x="113" y="-984.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
+<text text-anchor="start" x="113" y="-973.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
+<text text-anchor="start" x="113" y="-962.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
+<text text-anchor="start" x="113" y="-951.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
+<text text-anchor="start" x="113" y="-940.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
+<text text-anchor="start" x="113" y="-929.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
+<text text-anchor="start" x="113" y="-918.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="113" y="-907.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="113" y="-896.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="113" y="-885.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="113" y="-874.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
+<text text-anchor="start" x="113" y="-863.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
+<text text-anchor="start" x="113" y="-852.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
+<polyline fill="none" stroke="#000000" points="105,-845.5 288,-845.5 "/>
+<text text-anchor="start" x="113" y="-833.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
+<text text-anchor="start" x="113" y="-822.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
+<text text-anchor="start" x="113" y="-811.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
+<text text-anchor="start" x="113" y="-800.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
+<text text-anchor="start" x="113" y="-789.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="113" y="-778.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="113" y="-767.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="113" y="-756.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="113" y="-745.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="113" y="-734.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="113" y="-723.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
+<text text-anchor="start" x="113" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
+<text text-anchor="start" x="113" y="-701.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
+<text text-anchor="start" x="113" y="-690.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="113" y="-679.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
+<text text-anchor="start" x="113" y="-668.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
+<text text-anchor="start" x="113" y="-657.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
+<text text-anchor="start" x="113" y="-646.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
</a>
</g>
</g>
<!-- Node1->Node0 -->
<g id="edge1" class="edge">
<title>Node1->Node0</title>
-<path fill="none" stroke="#191970" d="M194,-629.1635C194,-620.1306 194,-611.2331 194,-602.575"/>
-<polygon fill="none" stroke="#191970" points="190.5001,-629.414 194,-639.4141 197.5001,-629.4141 190.5001,-629.414"/>
+<path fill="none" stroke="#191970" d="M196.5,-629.1635C196.5,-620.1306 196.5,-611.2331 196.5,-602.575"/>
+<polygon fill="none" stroke="#191970" points="193.0001,-629.414 196.5,-639.4141 200.0001,-629.4141 193.0001,-629.414"/>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable-members.html b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable-members.html
index b96bac21b..5119d8a6b 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable-members.html
@@ -92,26 +92,28 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#abd6d000714e0ed2b3b2f435ea5bd9a43">tvm::runtime::ModuleNode::GetFunction</a>(const std::string &name, bool query_imports=false)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a6b0965685d7ffb620f9ab317b67ce86d">GetFunctionArity</a>(std::string func) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#ab357b669cc14655ec68e5ecbdbdbb21a">GetFunctionParameterName</a>(std::string func, uint32_t index) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aabfeb049c4a50df7b204b34f56b31567">GetLib</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a726972ff315c446192df94027ddea032">GetOrAllocRuntimeTypeIndex</a>(const std::string &key, uint32_t static_tindex, uint32_t parent_tindex, uint32_t type_child_slots, bool type_child_slots_can_overflow)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">static</span [...]
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a73471876de99d185318d6e569c1ee709">GetPrimitives</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a73ac521892f4263554116261303e7e44">GetSource</a>(const std::string &format="")</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4d951e51832081b85875669eac90e940">GetTypeKey</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a5693cbadcc1168b96db7b1cc5c200b86">GetTypeKeyHash</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a2f0abfbed7ce24b365470c70db023ad3">GetVirtualDevices</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#af9c500be684a1a1dd0b69576827e9e34">GetVMFunctionWithName</a>(const std::string &func_name) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a9a808f0c63ae0d65ad8d625e3a7cb749">global_map</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a479da288ec1ca197e7fd353b7858f211">host_device_index</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a722ffdb3de3e1150b382c895af7dcb34">ImplementsFunction</a>(const String &name, bool query_imports=false)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a79b98521b484d1c672b7ce2ae2aed2b5">Import</a>(Module other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a12d5336240ba02a581bbb8a628a8cdb9">imports</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#af05db5c6d76f9b4dbf0631815170c5a7">imports_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac9e5eed7719e322117bde996a171e33a">IncRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#adc9c1b47c527f9fa2835ed3662c7d198">IsDSOExportable</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a25b1940338c004e93d68129c1e9190d3">late_bound_constant_names</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a4eeb4c5cfb8830d32d96756fd1dc58d0">Load</a>(const std::string &code, const runtime::Module lib)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a09a77db67e7e8a01be05f844d3f3dd53">LoadLateBoundConstantsFromFile</a>(const std::string &path)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#ad0dd5c8b70a9c2aff7e0a0517de53e0c">GetLateBoundConstants</a>(size_t byte_limit)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aabfeb049c4a50df7b204b34f56b31567">GetLib</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a726972ff315c446192df94027ddea032">GetOrAllocRuntimeTypeIndex</a>(const std::string &key, uint32_t static_tindex, uint32_t parent_tindex, uint32_t type_child_slots, bool type_child_slots_can_overflow)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a73471876de99d185318d6e569c1ee709">GetPrimitives</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a73ac521892f4263554116261303e7e44">GetSource</a>(const std::string &format="")</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4d951e51832081b85875669eac90e940">GetTypeKey</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a5693cbadcc1168b96db7b1cc5c200b86">GetTypeKeyHash</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a2f0abfbed7ce24b365470c70db023ad3">GetVirtualDevices</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#af9c500be684a1a1dd0b69576827e9e34">GetVMFunctionWithName</a>(const std::string &func_name) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a9a808f0c63ae0d65ad8d625e3a7cb749">global_map</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a479da288ec1ca197e7fd353b7858f211">host_device_index</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a722ffdb3de3e1150b382c895af7dcb34">ImplementsFunction</a>(const String &name, bool query_imports=false)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a79b98521b484d1c672b7ce2ae2aed2b5">Import</a>(Module other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a12d5336240ba02a581bbb8a628a8cdb9">imports</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#af05db5c6d76f9b4dbf0631815170c5a7">imports_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac9e5eed7719e322117bde996a171e33a">IncRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#adc9c1b47c527f9fa2835ed3662c7d198">IsDSOExportable</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a25b1940338c004e93d68129c1e9190d3">late_bound_constant_names</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a4eeb4c5cfb8830d32d96756fd1dc58d0">Load</a>(const std::string &code, const runtime::Module lib)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a09a77db67e7e8a01be05f844d3f3dd53">LoadLateBoundConstantsFromFile</a>(const std::string &path)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aa1e52496153fc99ed66db7ca54e1a3fc">LoadLateBoundConstantsFromMap</a>(Map< String, NDArray > map)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a2c01fd2724008842e2fff9b7cf6eab33">LoadLateBoundConstantsFromStream</a>(dmlc::Stream *stream)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#acfc071459e4cbdf522d3a10aea3f4887">MoveLateBoundConstantsToFile</a>(const std::string &path, size_t byte_limit)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a80391b52ca13b9123f245366e0fae2ef">MoveLateBoundConstantsToStream</a>(dmlc::Stream *stream, size_t byte_limit)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></td><td class="entry"></td></tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable.html b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable.html
index 646b2c3dc..afbd2dc23 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable.html
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable.html
@@ -109,9 +109,15 @@ Public Member Functions</h2></td></tr>
<tr class="memitem:acfc071459e4cbdf522d3a10aea3f4887"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#acfc071459e4cbdf522d3a10aea3f4887">MoveLateBoundConstantsToFile</a> (const std::string &path, size_t byte_limit)</td></tr>
<tr class="memdesc:acfc071459e4cbdf522d3a10aea3f4887"><td class="mdescLeft"> </td><td class="mdescRight">As for <code>MoveLateBoundConstantsToStream</code>, but save to file at <code>path</code>. <a href="#acfc071459e4cbdf522d3a10aea3f4887">More...</a><br /></td></tr>
<tr class="separator:acfc071459e4cbdf522d3a10aea3f4887"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ad0dd5c8b70a9c2aff7e0a0517de53e0c"><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_1runtime_1_1String.html">String</a>, <a class="el" href="classtvm_1_1runtime_1_1NDArray.html">NDArray</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#ad0dd5c8b70a9c2aff7e0a0517de53e0c">GetLateBoundConstants</a> (si [...]
+<tr class="memdesc:ad0dd5c8b70a9c2aff7e0a0517de53e0c"><td class="mdescLeft"> </td><td class="mdescRight">Get a map of all constants with larger that byte_limit in size. <a href="#ad0dd5c8b70a9c2aff7e0a0517de53e0c">More...</a><br /></td></tr>
+<tr class="separator:ad0dd5c8b70a9c2aff7e0a0517de53e0c"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a2c01fd2724008842e2fff9b7cf6eab33"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a2c01fd2724008842e2fff9b7cf6eab33">LoadLateBoundConstantsFromStream</a> (dmlc::Stream *stream)</td></tr>
<tr class="memdesc:a2c01fd2724008842e2fff9b7cf6eab33"><td class="mdescLeft"> </td><td class="mdescRight">Restores the late-bound constants for the executable (if any) from given byte-stream. <a href="#a2c01fd2724008842e2fff9b7cf6eab33">More...</a><br /></td></tr>
<tr class="separator:a2c01fd2724008842e2fff9b7cf6eab33"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aa1e52496153fc99ed66db7ca54e1a3fc"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aa1e52496153fc99ed66db7ca54e1a3fc">LoadLateBoundConstantsFromMap</a> (<a class="el" href="classtvm_1_1runtime_1_1Map.html">Map</a>< <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a>, <a class="el" href="classtvm_1_1runtime_1_1NDArray.html">NDArra [...]
+<tr class="memdesc:aa1e52496153fc99ed66db7ca54e1a3fc"><td class="mdescLeft"> </td><td class="mdescRight">Restores the late-bound constants for the executable (if any) from given map. <a href="#aa1e52496153fc99ed66db7ca54e1a3fc">More...</a><br /></td></tr>
+<tr class="separator:aa1e52496153fc99ed66db7ca54e1a3fc"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a09a77db67e7e8a01be05f844d3f3dd53"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a09a77db67e7e8a01be05f844d3f3dd53">LoadLateBoundConstantsFromFile</a> (const std::string &path)</td></tr>
<tr class="memdesc:a09a77db67e7e8a01be05f844d3f3dd53"><td class="mdescLeft"> </td><td class="mdescRight">As for <code>LoadLateBoundConstantsFromStream</code>, but load from file at <code>path</code>. <a href="#a09a77db67e7e8a01be05f844d3f3dd53">More...</a><br /></td></tr>
<tr class="separator:a09a77db67e7e8a01be05f844d3f3dd53"><td class="memSeparator" colspan="2"> </td></tr>
@@ -502,6 +508,26 @@ Additional Inherited Members</h2></td></tr>
</dl>
<dl class="section return"><dt>Returns</dt><dd>The parameter name. </dd></dl>
+</div>
+</div>
+<a id="ad0dd5c8b70a9c2aff7e0a0517de53e0c"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#ad0dd5c8b70a9c2aff7e0a0517de53e0c">◆ </a></span>GetLateBoundConstants()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname"><a class="el" href="classtvm_1_1runtime_1_1Map.html">Map</a><<a class="el" href="classtvm_1_1runtime_1_1String.html">String</a>, <a class="el" href="classtvm_1_1runtime_1_1NDArray.html">NDArray</a>> tvm::runtime::vm::Executable::GetLateBoundConstants </td>
+ <td>(</td>
+ <td class="paramtype">size_t </td>
+ <td class="paramname"><em>byte_limit</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Get a map of all constants with larger that byte_limit in size. </p>
+
</div>
</div>
<a id="aabfeb049c4a50df7b204b34f56b31567"></a>
@@ -654,6 +680,27 @@ Additional Inherited Members</h2></td></tr>
<p>As for <code>LoadLateBoundConstantsFromStream</code>, but load from file at <code>path</code>. </p>
+</div>
+</div>
+<a id="aa1e52496153fc99ed66db7ca54e1a3fc"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#aa1e52496153fc99ed66db7ca54e1a3fc">◆ </a></span>LoadLateBoundConstantsFromMap()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void tvm::runtime::vm::Executable::LoadLateBoundConstantsFromMap </td>
+ <td>(</td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Map.html">Map</a>< <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a>, <a class="el" href="classtvm_1_1runtime_1_1NDArray.html">NDArray</a> > </td>
+ <td class="paramname"><em>map</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Restores the late-bound constants for the executable (if any) from given map. </p>
+<p>Must be called after <code>Load</code> but before any other methods if <code>MoveLateBoundConstantsToBinary</code> was used when saving. Otherwise can be ignored. </p>
+
</div>
</div>
<a id="a2c01fd2724008842e2fff9b7cf6eab33"></a>
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable__coll__graph.svg
index 22c9a31f4..4605db777 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable__coll__graph.svg
@@ -12,34 +12,34 @@
<!-- Node3 -->
<g id="node1" class="node">
<title>Node3</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="4.5,-.5 4.5,-299.5 204.5,-299.5 204.5,-.5 4.5,-.5"/>
+<polygon fill="#bfbfbf" stroke="#000000" points="3,-.5 3,-299.5 206,-299.5 206,-.5 3,-.5"/>
<text text-anchor="middle" x="104.5" y="-287.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Executable</text>
-<polyline fill="none" stroke="#000000" points="4.5,-280.5 204.5,-280.5 "/>
-<text text-anchor="start" x="12.5" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ virtual_devices</text>
-<text text-anchor="start" x="12.5" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ host_device_index</text>
-<text text-anchor="start" x="12.5" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ constants</text>
-<text text-anchor="start" x="12.5" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ late_bound_constant</text>
-<text text-anchor="start" x="12.5" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_names</text>
-<text text-anchor="start" x="12.5" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ global_map</text>
-<text text-anchor="start" x="12.5" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ primitive_map</text>
-<text text-anchor="start" x="12.5" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ op_attrs</text>
-<text text-anchor="start" x="12.5" y="-180.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ functions</text>
-<text text-anchor="start" x="12.5" y="-169.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ const_device_indexes</text>
-<polyline fill="none" stroke="#000000" points="4.5,-162.5 204.5,-162.5 "/>
-<text text-anchor="start" x="12.5" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="12.5" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
-<text text-anchor="start" x="12.5" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
-<text text-anchor="start" x="12.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Save()</text>
-<text text-anchor="start" x="12.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsTo</text>
-<text text-anchor="start" x="12.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
-<text text-anchor="start" x="12.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsToFile()</text>
-<text text-anchor="start" x="12.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFrom</text>
-<text text-anchor="start" x="12.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
-<text text-anchor="start" x="12.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromFile()</text>
-<text text-anchor="start" x="12.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetBytecode()</text>
-<text text-anchor="start" x="12.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetConstants()</text>
-<text text-anchor="start" x="12.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 10 more...</text>
-<text text-anchor="start" x="12.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Load()</text>
+<polyline fill="none" stroke="#000000" points="3,-280.5 206,-280.5 "/>
+<text text-anchor="start" x="11" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ virtual_devices</text>
+<text text-anchor="start" x="11" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ host_device_index</text>
+<text text-anchor="start" x="11" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ constants</text>
+<text text-anchor="start" x="11" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ late_bound_constant</text>
+<text text-anchor="start" x="11" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_names</text>
+<text text-anchor="start" x="11" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ global_map</text>
+<text text-anchor="start" x="11" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ primitive_map</text>
+<text text-anchor="start" x="11" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ op_attrs</text>
+<text text-anchor="start" x="11" y="-180.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ functions</text>
+<text text-anchor="start" x="11" y="-169.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ const_device_indexes</text>
+<polyline fill="none" stroke="#000000" points="3,-162.5 206,-162.5 "/>
+<text text-anchor="start" x="11" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="11" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
+<text text-anchor="start" x="11" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
+<text text-anchor="start" x="11" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Save()</text>
+<text text-anchor="start" x="11" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsTo</text>
+<text text-anchor="start" x="11" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
+<text text-anchor="start" x="11" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsToFile()</text>
+<text text-anchor="start" x="11" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetLateBoundConstants()</text>
+<text text-anchor="start" x="11" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFrom</text>
+<text text-anchor="start" x="11" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
+<text text-anchor="start" x="11" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromMap()</text>
+<text text-anchor="start" x="11" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromFile()</text>
+<text text-anchor="start" x="11" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
+<text text-anchor="start" x="11" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Load()</text>
</g>
<!-- Node4 -->
<g id="node2" class="node">
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable__inherit__graph.svg
index 302d0b8d9..04cda722e 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1Executable__inherit__graph.svg
@@ -12,34 +12,34 @@
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="4.5,-.5 4.5,-299.5 204.5,-299.5 204.5,-.5 4.5,-.5"/>
+<polygon fill="#bfbfbf" stroke="#000000" points="3,-.5 3,-299.5 206,-299.5 206,-.5 3,-.5"/>
<text text-anchor="middle" x="104.5" y="-287.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Executable</text>
-<polyline fill="none" stroke="#000000" points="4.5,-280.5 204.5,-280.5 "/>
-<text text-anchor="start" x="12.5" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ virtual_devices</text>
-<text text-anchor="start" x="12.5" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ host_device_index</text>
-<text text-anchor="start" x="12.5" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ constants</text>
-<text text-anchor="start" x="12.5" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ late_bound_constant</text>
-<text text-anchor="start" x="12.5" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_names</text>
-<text text-anchor="start" x="12.5" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ global_map</text>
-<text text-anchor="start" x="12.5" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ primitive_map</text>
-<text text-anchor="start" x="12.5" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ op_attrs</text>
-<text text-anchor="start" x="12.5" y="-180.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ functions</text>
-<text text-anchor="start" x="12.5" y="-169.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ const_device_indexes</text>
-<polyline fill="none" stroke="#000000" points="4.5,-162.5 204.5,-162.5 "/>
-<text text-anchor="start" x="12.5" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="12.5" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
-<text text-anchor="start" x="12.5" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
-<text text-anchor="start" x="12.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Save()</text>
-<text text-anchor="start" x="12.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsTo</text>
-<text text-anchor="start" x="12.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
-<text text-anchor="start" x="12.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsToFile()</text>
-<text text-anchor="start" x="12.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFrom</text>
-<text text-anchor="start" x="12.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
-<text text-anchor="start" x="12.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromFile()</text>
-<text text-anchor="start" x="12.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetBytecode()</text>
-<text text-anchor="start" x="12.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetConstants()</text>
-<text text-anchor="start" x="12.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 10 more...</text>
-<text text-anchor="start" x="12.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Load()</text>
+<polyline fill="none" stroke="#000000" points="3,-280.5 206,-280.5 "/>
+<text text-anchor="start" x="11" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ virtual_devices</text>
+<text text-anchor="start" x="11" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ host_device_index</text>
+<text text-anchor="start" x="11" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ constants</text>
+<text text-anchor="start" x="11" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ late_bound_constant</text>
+<text text-anchor="start" x="11" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_names</text>
+<text text-anchor="start" x="11" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ global_map</text>
+<text text-anchor="start" x="11" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ primitive_map</text>
+<text text-anchor="start" x="11" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ op_attrs</text>
+<text text-anchor="start" x="11" y="-180.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ functions</text>
+<text text-anchor="start" x="11" y="-169.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ const_device_indexes</text>
+<polyline fill="none" stroke="#000000" points="3,-162.5 206,-162.5 "/>
+<text text-anchor="start" x="11" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="11" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
+<text text-anchor="start" x="11" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
+<text text-anchor="start" x="11" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Save()</text>
+<text text-anchor="start" x="11" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsTo</text>
+<text text-anchor="start" x="11" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
+<text text-anchor="start" x="11" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsToFile()</text>
+<text text-anchor="start" x="11" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetLateBoundConstants()</text>
+<text text-anchor="start" x="11" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFrom</text>
+<text text-anchor="start" x="11" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
+<text text-anchor="start" x="11" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromMap()</text>
+<text text-anchor="start" x="11" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromFile()</text>
+<text text-anchor="start" x="11" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
+<text text-anchor="start" x="11" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Load()</text>
</g>
<!-- Node1 -->
<g id="node2" class="node">
diff --git a/docs/reference/api/doxygen/executable_8h_source.html b/docs/reference/api/doxygen/executable_8h_source.html
index 0186fccc9..eda10cd44 100644
--- a/docs/reference/api/doxygen/executable_8h_source.html
+++ b/docs/reference/api/doxygen/executable_8h_source.html
@@ -66,30 +66,31 @@ $(function() {
<div class="title">executable.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="executable_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more [...]
+<a href="executable_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more [...]
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html">tvm::runtime::vm::Executable</a></div><div class="ttdoc">The executable emitted by the VM compiler. </div><div class="ttdef"><b>Definition:</b> executable.h:57</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectPtr_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectPtr.html">tvm::runtime::ObjectPtr</a></div><div class="ttdoc">A custom smart pointer for Object. </div><div class="ttdef"><b>Definition:</b> object.h:358</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_af7d75150b6a98a7766a552d7e7e34a11"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#af7d75150b6a98a7766a552d7e7e34a11">tvm::runtime::vm::Executable::functions</a></div><div class="ttdeci">std::vector< VMFunction > functions</div><div class="ttdoc">The virtual machine&#39;s function table. </div><div class="ttdef"><b>Definition:</b> executable.h:279</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_af7d75150b6a98a7766a552d7e7e34a11"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#af7d75150b6a98a7766a552d7e7e34a11">tvm::runtime::vm::Executable::functions</a></div><div class="ttdeci">std::vector< VMFunction > functions</div><div class="ttdoc">The virtual machine&#39;s function table. </div><div class="ttdef"><b>Definition:</b> executable.h:292</div></div>
<div class="ttc" id="string_8h_html"><div class="ttname"><a href="string_8h.html">string.h</a></div><div class="ttdoc">Runtime String container types. </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="classtvm_1_1runtime_1_1vm_1_1Executable_html_a64a56d507939eee688f485057a2c7d2e"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a64a56d507939eee688f485057a2c7d2e">tvm::runtime::vm::Executable::constants</a></div><div class="ttdeci">std::vector< ObjectRef > constants</div><div class="ttdoc">The global constant array. </div><div class="ttdef"><b>Definition:</b> executable.h:263</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a64a56d507939eee688f485057a2c7d2e"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a64a56d507939eee688f485057a2c7d2e">tvm::runtime::vm::Executable::constants</a></div><div class="ttdeci">std::vector< ObjectRef > constants</div><div class="ttdoc">The global constant array. </div><div class="ttdef"><b>Definition:</b> executable.h:276</div></div>
<div class="ttc" id="structTVMByteArray_html"><div class="ttname"><a href="structTVMByteArray.html">TVMByteArray</a></div><div class="ttdoc">Byte array type used to pass in byte array When kTVMBytes is used as data type. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:157</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a46b765fff87620da472fa15caf80e1d5"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a46b765fff87620da472fa15caf80e1d5">tvm::runtime::vm::Executable::const_device_indexes</a></div><div class="ttdeci">std::vector< Index > const_device_indexes</div><div class="ttdoc">The index of the device holding each constant. </div><div class="ttdef"><b>Definition:</b> executable.h:281</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_ab5a31e8670a4f20564abc48610a90e8c"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#ab5a31e8670a4f20564abc48610a90e8c">tvm::runtime::vm::Executable::primitive_map</a></div><div class="ttdeci">std::unordered_map< std::string, Index > primitive_map</div><div class="ttdoc">A mapping from the packed function&#39;s global name (as string) to the index that corresponds to the pos...</div><div c [...]
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_aef4f3663ee57fcbdf2d775f4dbbe79dc"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aef4f3663ee57fcbdf2d775f4dbbe79dc">tvm::runtime::vm::Executable::type_key</a></div><div class="ttdeci">const char * type_key() const final</div><div class="ttdef"><b>Definition:</b> executable.h:245</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a46b765fff87620da472fa15caf80e1d5"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a46b765fff87620da472fa15caf80e1d5">tvm::runtime::vm::Executable::const_device_indexes</a></div><div class="ttdeci">std::vector< Index > const_device_indexes</div><div class="ttdoc">The index of the device holding each constant. </div><div class="ttdef"><b>Definition:</b> executable.h:294</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_ab5a31e8670a4f20564abc48610a90e8c"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#ab5a31e8670a4f20564abc48610a90e8c">tvm::runtime::vm::Executable::primitive_map</a></div><div class="ttdeci">std::unordered_map< std::string, Index > primitive_map</div><div class="ttdoc">A mapping from the packed function&#39;s global name (as string) to the index that corresponds to the pos...</div><div c [...]
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_aef4f3663ee57fcbdf2d775f4dbbe79dc"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aef4f3663ee57fcbdf2d775f4dbbe79dc">tvm::runtime::vm::Executable::type_key</a></div><div class="ttdeci">const char * type_key() const final</div><div class="ttdef"><b>Definition:</b> executable.h:258</div></div>
<div class="ttc" id="bytecode_8h_html"><div class="ttname"><a href="bytecode_8h.html">bytecode.h</a></div><div class="ttdoc">The bytecode for Relay virtual machine. </div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a9a808f0c63ae0d65ad8d625e3a7cb749"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a9a808f0c63ae0d65ad8d625e3a7cb749">tvm::runtime::vm::Executable::global_map</a></div><div class="ttdeci">std::unordered_map< std::string, Index > global_map</div><div class="ttdoc">A map from globals (as strings) to their index in the Relay function map. </div><div class="ttdef"><b>Definition:</b> executable.h [...]
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a25b1940338c004e93d68129c1e9190d3"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a25b1940338c004e93d68129c1e9190d3">tvm::runtime::vm::Executable::late_bound_constant_names</a></div><div class="ttdeci">std::vector< String > late_bound_constant_names</div><div class="ttdoc">For each constant index the name of the late-bound constant, or null if constant is immediate...</div><div class="ttdef [...]
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a9a808f0c63ae0d65ad8d625e3a7cb749"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a9a808f0c63ae0d65ad8d625e3a7cb749">tvm::runtime::vm::Executable::global_map</a></div><div class="ttdeci">std::unordered_map< std::string, Index > global_map</div><div class="ttdoc">A map from globals (as strings) to their index in the Relay function map. </div><div class="ttdef"><b>Definition:</b> executable.h [...]
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a25b1940338c004e93d68129c1e9190d3"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a25b1940338c004e93d68129c1e9190d3">tvm::runtime::vm::Executable::late_bound_constant_names</a></div><div class="ttdeci">std::vector< String > late_bound_constant_names</div><div class="ttdoc">For each constant index the name of the late-bound constant, or null if constant is immediate...</div><div class="ttdef [...]
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1VMFunction_html"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html">tvm::runtime::vm::VMFunction</a></div><div class="ttdoc">A representation of a Relay function in the VM. </div><div class="ttdef"><b>Definition:</b> vm.h:77</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ModuleNode_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></div><div class="ttdoc">Base container of module. </div><div class="ttdef"><b>Definition:</b> module.h:113</div></div>
<div class="ttc" id="object_8h_html"><div class="ttname"><a href="object_8h.html">object.h</a></div><div class="ttdoc">A managed object in the TVM runtime. </div></div>
<div class="ttc" id="runtime_2module_8h_html"><div class="ttname"><a href="runtime_2module_8h.html">module.h</a></div><div class="ttdoc">Runtime container of the functions generated by TVM, This is used to support dynamically link...</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Module_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Module.html">tvm::runtime::Module</a></div><div class="ttdoc">Module container of TVM. </div><div class="ttdef"><b>Definition:</b> module.h:50</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_aae6b6508e423538a82c23a1724c87877"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aae6b6508e423538a82c23a1724c87877">tvm::runtime::vm::Executable::virtual_devices</a></div><div class="ttdeci">std::vector< Device > virtual_devices</div><div class="ttdoc">The (compile-time, virtual) devices corresponding to each device index. Currently we only support at ...</div><div class="ttdef"><b>Definit [...]
+<div class="ttc" id="classtvm_1_1runtime_1_1Map_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Map.html">tvm::runtime::Map</a></div><div class="ttdoc">Map container of NodeRef->NodeRef in DSL graph. Map implements copy on write semantics, which means map is mutable but copy will happen when array is referenced in more than two places. </div><div class="ttdef"><b>Definition:</b> map.h:1268</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_aae6b6508e423538a82c23a1724c87877"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aae6b6508e423538a82c23a1724c87877">tvm::runtime::vm::Executable::virtual_devices</a></div><div class="ttdeci">std::vector< Device > virtual_devices</div><div class="ttdoc">The (compile-time, virtual) devices corresponding to each device index. Currently we only support at ...</div><div class="ttdef"><b>Definit [...]
<div class="ttc" id="map_8h_html"><div class="ttname"><a href="map_8h.html">map.h</a></div><div class="ttdoc">Runtime Map container types. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1PackedFunc_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1PackedFunc.html">tvm::runtime::PackedFunc</a></div><div class="ttdoc">Packed function is a type-erased function. The arguments are passed by packed format. </div><div class="ttdef"><b>Definition:</b> packed_func.h:138</div></div>
<div class="ttc" id="packed__func_8h_html"><div class="ttname"><a href="packed__func_8h.html">packed_func.h</a></div><div class="ttdoc">Type-erased function used across TVM API. </div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a99432cdf9ce74de84f08feec9b08ed5e"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a99432cdf9ce74de84f08feec9b08ed5e">tvm::runtime::vm::Executable::~Executable</a></div><div class="ttdeci">virtual ~Executable()</div><div class="ttdef"><b>Definition:</b> executable.h:243</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Executable_html_a99432cdf9ce74de84f08feec9b08ed5e"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a99432cdf9ce74de84f08feec9b08ed5e">tvm::runtime::vm::Executable::~Executable</a></div><div class="ttdeci">virtual ~Executable()</div><div class="ttdef"><b>Definition:</b> executable.h:256</div></div>
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/functions_func_g.html b/docs/reference/api/doxygen/functions_func_g.html
index 7c15a79fd..7529754cb 100644
--- a/docs/reference/api/doxygen/functions_func_g.html
+++ b/docs/reference/api/doxygen/functions_func_g.html
@@ -292,6 +292,9 @@ $(function() {
<li>GetLastFrame()
: <a class="el" href="classtvm_1_1script_1_1ir__builder_1_1IRBuilderNode.html#a8f8071bc13ae7d04ab49111ecc472027">tvm::script::ir_builder::IRBuilderNode</a>
</li>
+<li>GetLateBoundConstants()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#ad0dd5c8b70a9c2aff7e0a0517de53e0c">tvm::runtime::vm::Executable</a>
+</li>
<li>GetLib()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aabfeb049c4a50df7b204b34f56b31567">tvm::runtime::vm::Executable</a>
</li>
@@ -360,7 +363,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypeReporterNode.html#a06af835a761aaa10627a88ac4b712a15">tvm::TypeReporterNode</a>
</li>
<li>GetSRef()
-: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a34d50e4b429557302c5c6575bcc706d5">tvm::tir::ScheduleNode</a>
+: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a2a52c8522a4bfc7d42a189250a462ce8">tvm::tir::ScheduleNode</a>
</li>
<li>GetTag()
: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a8b46d1eb3853555b6d3a85f2ef9c0868">tvm::runtime::vm::Instruction</a>
@@ -398,7 +401,7 @@ $(function() {
: <a class="el" href="classtvm_1_1GlobalVar.html#a09f3b31e7ddde86012b7e92fe1986e4d">tvm::GlobalVar</a>
</li>
<li>GlobalVarSupply()
-: <a class="el" href="classtvm_1_1GlobalVarSupply.html#a0eaceb757342679afa02708f290ff995">tvm::GlobalVarSupply</a>
+: <a class="el" href="classtvm_1_1GlobalVarSupply.html#a7495cd6b47551c159691658f77c8adc2">tvm::GlobalVarSupply</a>
</li>
<li>GlobalVarSupplyNode()
: <a class="el" href="classtvm_1_1GlobalVarSupplyNode.html#afc86b0c452c4e95050b4e3fc3a19391f">tvm::GlobalVarSupplyNode</a>
diff --git a/docs/reference/api/doxygen/functions_func_l.html b/docs/reference/api/doxygen/functions_func_l.html
index efe526d96..dc615b96c 100644
--- a/docs/reference/api/doxygen/functions_func_l.html
+++ b/docs/reference/api/doxygen/functions_func_l.html
@@ -175,6 +175,9 @@ $(function() {
<li>LoadLateBoundConstantsFromFile()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a09a77db67e7e8a01be05f844d3f3dd53">tvm::runtime::vm::Executable</a>
</li>
+<li>LoadLateBoundConstantsFromMap()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aa1e52496153fc99ed66db7ca54e1a3fc">tvm::runtime::vm::Executable</a>
+</li>
<li>LoadLateBoundConstantsFromStream()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a2c01fd2724008842e2fff9b7cf6eab33">tvm::runtime::vm::Executable</a>
</li>
@@ -197,7 +200,7 @@ $(function() {
: <a class="el" href="classtvm_1_1IRModuleNode.html#ae078ad8def39579701d144578c787bcf">tvm::IRModuleNode</a>
</li>
<li>LookupTypeDef()
-: <a class="el" href="classtvm_1_1IRModuleNode.html#ae095c1fd87642bd417224668c5b4d910">tvm::IRModuleNode</a>
+: <a class="el" href="classtvm_1_1IRModuleNode.html#a23f3769fe60b3b06c9d163650ea7caaf">tvm::IRModuleNode</a>
</li>
<li>LoopRV()
: <a class="el" href="classtvm_1_1tir_1_1LoopRV.html#ad47c4e83701875b84c9efd36ee3dc323">tvm::tir::LoopRV</a>
diff --git a/docs/reference/api/doxygen/functions_func_t.html b/docs/reference/api/doxygen/functions_func_t.html
index b0d462bd8..1b7e969ff 100644
--- a/docs/reference/api/doxygen/functions_func_t.html
+++ b/docs/reference/api/doxygen/functions_func_t.html
@@ -1132,7 +1132,7 @@ $(function() {
: <a class="el" href="classtvm_1_1runtime_1_1TVMArgsSetter.html#a5882f7eda112e825eb5a87e45aeb85b0">tvm::runtime::TVMArgsSetter</a>
</li>
<li>TVMArgValue()
-: <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html#a5fbd71750e5bbba6edc9094178af9276">tvm::runtime::TVMArgValue</a>
+: <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html#a987b2fb283cea5484d4655e3f711c046">tvm::runtime::TVMArgValue</a>
</li>
<li>TVMMovableArgValue_()
: <a class="el" href="classtvm_1_1runtime_1_1TVMMovableArgValue__.html#a8eca9048535541f374a5806f9648131b">tvm::runtime::TVMMovableArgValue_</a>
@@ -1173,7 +1173,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a41a6b9014d0feeb628ca7edfd0d26f0b">tvm::TypedEnvFunc< R(Args...)></a>
</li>
<li>TypedPackedFunc()
-: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a4abadc6786dd14a3aed6e2b5b342d1d6">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a8941c80982a1b2a289440f3c79bb0ac8">tvm::runtime::TypedPackedFunc< R(Args...)></a>
</li>
<li>TypeIndex2Key()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
@@ -1196,7 +1196,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypeRelation.html#ac26b1897eab8197ed26606ab81b7403b">tvm::TypeRelation</a>
</li>
<li>TypeReporter()
-: <a class="el" href="classtvm_1_1TypeReporter.html#aa3dc38a3c84d324d0b3a9f358460a091">tvm::TypeReporter</a>
+: <a class="el" href="classtvm_1_1TypeReporter.html#a8e7e05a07f9f7ad9bea91f27afac9051">tvm::TypeReporter</a>
</li>
<li>TypeVar()
: <a class="el" href="classtvm_1_1TypeVar.html#adf5ef8e89d162735519b5d125c89e3e3">tvm::TypeVar</a>
diff --git a/docs/reference/api/doxygen/functions_func_u.html b/docs/reference/api/doxygen/functions_func_u.html
index 31fb74a2d..88e21c212 100644
--- a/docs/reference/api/doxygen/functions_func_u.html
+++ b/docs/reference/api/doxygen/functions_func_u.html
@@ -103,7 +103,7 @@ $(function() {
, <a class="el" href="classtvm_1_1auto__scheduler_1_1CostModelNode.html#ae35b2b678760b8da57a43d3ae9c24da5">tvm::auto_scheduler::CostModelNode</a>
, <a class="el" href="classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#a2d7849df6c7dbe93bf363c1d9f860a26">tvm::auto_scheduler::PythonBasedModelNode</a>
, <a class="el" href="classtvm_1_1auto__scheduler_1_1RandomModelNode.html#a7febac6c05d8e2d407f466467769ee32">tvm::auto_scheduler::RandomModelNode</a>
-, <a class="el" href="classtvm_1_1IRModuleNode.html#abdd8936c6fca33ef9b7c086f8fd58f84">tvm::IRModuleNode</a>
+, <a class="el" href="classtvm_1_1IRModuleNode.html#a94a93385e64ce844299729af6a573015">tvm::IRModuleNode</a>
, <a class="el" href="classtvm_1_1meta__schedule_1_1CostModelNode.html#a1bba32eba84db583fe90d1a5bce085f1">tvm::meta_schedule::CostModelNode</a>
, <a class="el" href="classtvm_1_1meta__schedule_1_1PyCostModelNode.html#a970b00b0eb1bf6b88eea2711b58c4d1d">tvm::meta_schedule::PyCostModelNode</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_g.html b/docs/reference/api/doxygen/functions_g.html
index 91f41c47a..b34f97622 100644
--- a/docs/reference/api/doxygen/functions_g.html
+++ b/docs/reference/api/doxygen/functions_g.html
@@ -298,6 +298,9 @@ $(function() {
<li>GetLastFrame()
: <a class="el" href="classtvm_1_1script_1_1ir__builder_1_1IRBuilderNode.html#a8f8071bc13ae7d04ab49111ecc472027">tvm::script::ir_builder::IRBuilderNode</a>
</li>
+<li>GetLateBoundConstants()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#ad0dd5c8b70a9c2aff7e0a0517de53e0c">tvm::runtime::vm::Executable</a>
+</li>
<li>GetLib()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aabfeb049c4a50df7b204b34f56b31567">tvm::runtime::vm::Executable</a>
</li>
@@ -375,7 +378,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypeReporterNode.html#a06af835a761aaa10627a88ac4b712a15">tvm::TypeReporterNode</a>
</li>
<li>GetSRef()
-: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a08f7ed1ef1470fb1c9cfc272e14a1e32">tvm::tir::ScheduleNode</a>
+: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a3b6d659b1a0a4b8175d7495afc3a791c">tvm::tir::ScheduleNode</a>
</li>
<li>GetTag()
: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a8b46d1eb3853555b6d3a85f2ef9c0868">tvm::runtime::vm::Instruction</a>
@@ -416,7 +419,7 @@ $(function() {
: <a class="el" href="classtvm_1_1GlobalVar.html#a09f3b31e7ddde86012b7e92fe1986e4d">tvm::GlobalVar</a>
</li>
<li>GlobalVarSupply()
-: <a class="el" href="classtvm_1_1GlobalVarSupply.html#a96877f1067ea9f027d326976edfca03f">tvm::GlobalVarSupply</a>
+: <a class="el" href="classtvm_1_1GlobalVarSupply.html#a7495cd6b47551c159691658f77c8adc2">tvm::GlobalVarSupply</a>
</li>
<li>GlobalVarSupplyNode()
: <a class="el" href="classtvm_1_1GlobalVarSupplyNode.html#adb8480ebe496dece012c527d292ac046">tvm::GlobalVarSupplyNode</a>
diff --git a/docs/reference/api/doxygen/functions_l.html b/docs/reference/api/doxygen/functions_l.html
index c9c275cf3..53d220b54 100644
--- a/docs/reference/api/doxygen/functions_l.html
+++ b/docs/reference/api/doxygen/functions_l.html
@@ -197,7 +197,7 @@ $(function() {
: <a class="el" href="classtvm_1_1transform_1_1PassContext.html#a04862282d920a116d62ede78b6a13a51">tvm::transform::PassContext</a>
</li>
<li>ListDoc()
-: <a class="el" href="classtvm_1_1script_1_1printer_1_1ListDoc.html#a6571c46f21621f03f68be9c11df16bb0">tvm::script::printer::ListDoc</a>
+: <a class="el" href="classtvm_1_1script_1_1printer_1_1ListDoc.html#a312edc2fe47a5d3839393ff21f9300b4">tvm::script::printer::ListDoc</a>
</li>
<li>ListExecutorOptions()
: <a class="el" href="classtvm_1_1relay_1_1Executor.html#aff01389fa805b31457fc6cbdce626d3b">tvm::relay::Executor</a>
@@ -256,6 +256,9 @@ $(function() {
<li>LoadLateBoundConstantsFromFile()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a09a77db67e7e8a01be05f844d3f3dd53">tvm::runtime::vm::Executable</a>
</li>
+<li>LoadLateBoundConstantsFromMap()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#aa1e52496153fc99ed66db7ca54e1a3fc">tvm::runtime::vm::Executable</a>
+</li>
<li>LoadLateBoundConstantsFromStream()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#a2c01fd2724008842e2fff9b7cf6eab33">tvm::runtime::vm::Executable</a>
</li>
@@ -282,7 +285,7 @@ $(function() {
: <a class="el" href="classtvm_1_1IRModuleNode.html#ae078ad8def39579701d144578c787bcf">tvm::IRModuleNode</a>
</li>
<li>LookupTypeDef()
-: <a class="el" href="classtvm_1_1IRModuleNode.html#a23f3769fe60b3b06c9d163650ea7caaf">tvm::IRModuleNode</a>
+: <a class="el" href="classtvm_1_1IRModuleNode.html#ae095c1fd87642bd417224668c5b4d910">tvm::IRModuleNode</a>
</li>
<li>loop_var
: <a class="el" href="classtvm_1_1tir_1_1ForNode.html#a7dbf66bdcf8ed397321517f0915a0946">tvm::tir::ForNode</a>
diff --git a/docs/reference/api/doxygen/functions_m.html b/docs/reference/api/doxygen/functions_m.html
index 0f1d2c239..63d1e1cf7 100644
--- a/docs/reference/api/doxygen/functions_m.html
+++ b/docs/reference/api/doxygen/functions_m.html
@@ -342,7 +342,7 @@ $(function() {
: <a class="el" href="classtvm_1_1DiagnosticContextNode.html#adea7e38a6e47cbab7fb5639f208aa536">tvm::DiagnosticContextNode</a>
</li>
<li>Module()
-: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abd1380b3f813c2b6acefca3aaef425f4">tvm::runtime::Module</a>
+: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9">tvm::runtime::Module</a>
, <a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d">tvm::runtime::ModuleNode</a>
</li>
<li>module_handle
diff --git a/docs/reference/api/doxygen/functions_s.html b/docs/reference/api/doxygen/functions_s.html
index 3b4ab797e..e6d5009a9 100644
--- a/docs/reference/api/doxygen/functions_s.html
+++ b/docs/reference/api/doxygen/functions_s.html
@@ -1000,7 +1000,7 @@ $(function() {
: <a class="el" href="classtvm_1_1script_1_1printer_1_1StmtDoc.html#adec8d59e41d8a4093fb310089bf2c3ba">tvm::script::printer::StmtDoc</a>
</li>
<li>StmtNode()
-: <a class="el" href="classtvm_1_1tir_1_1StmtNode.html#a67693c4e97ae49890ea74605fe1b1f74">tvm::tir::StmtNode</a>
+: <a class="el" href="classtvm_1_1tir_1_1StmtNode.html#a79e21b14d3ab57209577bf4a8f694a87">tvm::tir::StmtNode</a>
</li>
<li>stmts
: <a class="el" href="classtvm_1_1script_1_1printer_1_1StmtBlockDocNode.html#a17862bcb50fd1ef49cd9a47f065e612c">tvm::script::printer::StmtBlockDocNode</a>
@@ -1050,7 +1050,7 @@ $(function() {
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a93d1d23f24d903db844f75f51fe09a36">tvm::tir::ScheduleNode</a>
</li>
<li>StorageAlignStep()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1StorageAlignStep.html#af50b7c2f020f8e0a80f5bcc8e559b394">tvm::auto_scheduler::StorageAlignStep</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1StorageAlignStep.html#a99dbb8c55d9e7d78268b6d43fd348bc7">tvm::auto_scheduler::StorageAlignStep</a>
</li>
<li>StorageType
: <a class="el" href="classtvm_1_1runtime_1_1SimpleObjAllocator_1_1ArrayHandler.html#a67e86db3290b1d3bd4aca7e7a2faf187">tvm::runtime::SimpleObjAllocator::ArrayHandler< ArrayType, ElemType ></a>
diff --git a/docs/reference/api/doxygen/functions_t.html b/docs/reference/api/doxygen/functions_t.html
index dbe7fec74..11081dc3f 100644
--- a/docs/reference/api/doxygen/functions_t.html
+++ b/docs/reference/api/doxygen/functions_t.html
@@ -1341,7 +1341,7 @@ $(function() {
<li>TVMPODValue_
: <a class="el" href="classtvm_1_1runtime_1_1NDArray.html#a9a9fd94393cfd7d4b6e6029348e3e19a">tvm::runtime::NDArray</a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#a9a9fd94393cfd7d4b6e6029348e3e19a">tvm::runtime::ObjectPtr< T ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1TVMPODValue__.html#afe1837bdbafe8341c2031c5cebcf6e74">tvm::runtime::TVMPODValue_</a>
+, <a class="el" href="classtvm_1_1runtime_1_1TVMPODValue__.html#a2f46b59a6c1d5eb4575d7f583b5f1a0c">tvm::runtime::TVMPODValue_</a>
</li>
<li>TVMRetValue
: <a class="el" href="classtvm_1_1BaseAttrsNode.html#a1f56f080d0c1fab79d9469029aef8ebb">tvm::BaseAttrsNode</a>
diff --git a/docs/reference/api/doxygen/functions_u.html b/docs/reference/api/doxygen/functions_u.html
index 981d4ef19..73373a1b4 100644
--- a/docs/reference/api/doxygen/functions_u.html
+++ b/docs/reference/api/doxygen/functions_u.html
@@ -119,7 +119,7 @@ $(function() {
, <a class="el" href="classtvm_1_1auto__scheduler_1_1CostModelNode.html#ae35b2b678760b8da57a43d3ae9c24da5">tvm::auto_scheduler::CostModelNode</a>
, <a class="el" href="classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#a2d7849df6c7dbe93bf363c1d9f860a26">tvm::auto_scheduler::PythonBasedModelNode</a>
, <a class="el" href="classtvm_1_1auto__scheduler_1_1RandomModelNode.html#a7febac6c05d8e2d407f466467769ee32">tvm::auto_scheduler::RandomModelNode</a>
-, <a class="el" href="classtvm_1_1IRModuleNode.html#abdd8936c6fca33ef9b7c086f8fd58f84">tvm::IRModuleNode</a>
+, <a class="el" href="classtvm_1_1IRModuleNode.html#a94a93385e64ce844299729af6a573015">tvm::IRModuleNode</a>
, <a class="el" href="classtvm_1_1meta__schedule_1_1CostModelNode.html#a1bba32eba84db583fe90d1a5bce085f1">tvm::meta_schedule::CostModelNode</a>
, <a class="el" href="classtvm_1_1meta__schedule_1_1PyCostModelNode.html#a970b00b0eb1bf6b88eea2711b58c4d1d">tvm::meta_schedule::PyCostModelNode</a>
</li>
diff --git a/docs/reference/api/doxygen/search/all_11.js b/docs/reference/api/doxygen/search/all_11.js
index 130231d5f..00a3a34e8 100644
--- a/docs/reference/api/doxygen/search/all_11.js
+++ b/docs/reference/api/doxygen/search/all_11.js
@@ -34,7 +34,7 @@ var searchData=
['page_5fallocator_2eh',['page_allocator.h',['../page__allocator_8h.html',1,'']]],
['pagememorymanagercreate',['PageMemoryManagerCreate',['../page__allocator_8h.html#a720dbc7474ac13b93fafb974cfc20bc7',1,'page_allocator.h']]],
['papi_2eh',['papi.h',['../papi_8h.html',1,'']]],
- ['parallel',['parallel',['../classtvm_1_1auto__scheduler_1_1State.html#a2376f0180bc5b5dd4b456f2a75d4a366',1,'tvm::auto_scheduler::State::parallel()'],['../classtvm_1_1te_1_1Stage.html#a60a6be10a1a96cb594c1399efabafef3',1,'tvm::te::Stage::parallel()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a553dc17c0b49b175cd16881c81b6c789',1,'tvm::tir::ScheduleNode::Parallel()']]],
+ ['parallel',['Parallel',['../classtvm_1_1tir_1_1ScheduleNode.html#a553dc17c0b49b175cd16881c81b6c789',1,'tvm::tir::ScheduleNode::Parallel()'],['../classtvm_1_1auto__scheduler_1_1State.html#a2376f0180bc5b5dd4b456f2a75d4a366',1,'tvm::auto_scheduler::State::parallel()'],['../classtvm_1_1te_1_1Stage.html#a60a6be10a1a96cb594c1399efabafef3',1,'tvm::te::Stage::parallel()']]],
['parallel_5ffor',['parallel_for',['../namespacetvm_1_1support.html#a8bf1225e8bb1db575578ca2d645fb23c',1,'tvm::support']]],
['parallel_5ffor_2eh',['parallel_for.h',['../parallel__for_8h.html',1,'']]],
['parallel_5ffor_5fdynamic',['parallel_for_dynamic',['../namespacetvm_1_1support.html#afe4271363c794f1644ce7af5c2266530',1,'tvm::support']]],
@@ -69,7 +69,7 @@ var searchData=
['path',['path',['../classtvm_1_1relay_1_1DominatorPatternNode.html#a752951f9926f6011dc4d925fcca44c9a',1,'tvm::relay::DominatorPatternNode']]],
['pathsequal',['PathsEqual',['../classtvm_1_1ObjectPathNode.html#af3648f5578cd516a649237539467e387',1,'tvm::ObjectPathNode']]],
['pathtracingdata',['PathTracingData',['../classtvm_1_1SEqualReducer_1_1Handler.html#a3971c2653bf9bae74dd940cd80085aef',1,'tvm::SEqualReducer::Handler']]],
- ['pattern',['Pattern',['../classtvm_1_1relay_1_1Pattern.html',1,'tvm::relay::Pattern'],['../classtvm_1_1relay_1_1DFPatternCallbackNode.html#acfe3e9170d4c05ff59f3056b79ae58bb',1,'tvm::relay::DFPatternCallbackNode::pattern()'],['../classtvm_1_1relay_1_1TypePatternNode.html#a7273a1fa7c10a1c4a5f3a4d46bcd463a',1,'tvm::relay::TypePatternNode::pattern()'],['../classtvm_1_1relay_1_1ShapePatternNode.html#a77130ba4e4b1b051415a08a6c0148d30',1,'tvm::relay::ShapePatternNode::pattern()'],['../classt [...]
+ ['pattern',['Pattern',['../classtvm_1_1relay_1_1Pattern.html',1,'tvm::relay::Pattern'],['../classtvm_1_1relay_1_1Pattern.html#aba2fe5ab04ab0b56ff855cfc572b16ff',1,'tvm::relay::Pattern::Pattern()'],['../classtvm_1_1relay_1_1Pattern.html#ad2eae0030bb557fbee1b85517cd9c31e',1,'tvm::relay::Pattern::Pattern(ObjectPtr< tvm::Object > p)'],['../classtvm_1_1relay_1_1DFPatternCallbackNode.html#acfe3e9170d4c05ff59f3056b79ae58bb',1,'tvm::relay::DFPatternCallbackNode::pattern()'],['../classtvm [...]
['pattern_2eh',['pattern.h',['../pattern_8h.html',1,'']]],
['pattern_5ffunctor_2eh',['pattern_functor.h',['../pattern__functor_8h.html',1,'']]],
['pattern_5ffunctor_5fdefault',['PATTERN_FUNCTOR_DEFAULT',['../pattern__functor_8h.html#ac72a5016a4b58a73ed7e7652c7a876d7',1,'pattern_functor.h']]],
@@ -167,7 +167,7 @@ var searchData=
['predict_5ffunc',['predict_func',['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#aa051c804bc592d7f4f1a5b5710f73595',1,'tvm::auto_scheduler::PythonBasedModelNode']]],
['predict_5fstage_5ffunc',['predict_stage_func',['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#a380809fbb5d4d68b9ec744e3a5015fe6',1,'tvm::auto_scheduler::PythonBasedModelNode']]],
['predictstages',['PredictStages',['../classtvm_1_1auto__scheduler_1_1CostModelNode.html#a213222251099444874698d2e9ff18adc',1,'tvm::auto_scheduler::CostModelNode::PredictStages()'],['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#a1f9975c4bdd61793b806663a61a9a703',1,'tvm::auto_scheduler::PythonBasedModelNode::PredictStages()']]],
- ['prefetch',['Prefetch',['../classtvm_1_1tir_1_1Prefetch.html',1,'tvm::tir::Prefetch'],['../classtvm_1_1tir_1_1Prefetch.html#af462f85dad4268685e3113b6b009d1b2',1,'tvm::tir::Prefetch::Prefetch()'],['../classtvm_1_1te_1_1Stage.html#a611327890918fb641a8e65396ab9c5f6',1,'tvm::te::Stage::prefetch()'],['../namespacetvm_1_1tir_1_1builtin.html#a543f1fc334d2bc830add972895a03f17',1,'tvm::tir::builtin::prefetch()']]],
+ ['prefetch',['Prefetch',['../classtvm_1_1tir_1_1Prefetch.html',1,'tvm::tir::Prefetch'],['../classtvm_1_1te_1_1Stage.html#a611327890918fb641a8e65396ab9c5f6',1,'tvm::te::Stage::prefetch()'],['../classtvm_1_1tir_1_1Prefetch.html#af462f85dad4268685e3113b6b009d1b2',1,'tvm::tir::Prefetch::Prefetch()'],['../namespacetvm_1_1tir_1_1builtin.html#a543f1fc334d2bc830add972895a03f17',1,'tvm::tir::builtin::prefetch()']]],
['prefetch_5fdata',['prefetch_data',['../classtvm_1_1te_1_1IterVarAttrNode.html#a0cd129334ac1bc8d6461fb06be67e731',1,'tvm::te::IterVarAttrNode']]],
['prefetch_5foffset',['prefetch_offset',['../classtvm_1_1te_1_1IterVarAttrNode.html#a2a4a8e201e6caefeecffd4a7647866fd',1,'tvm::te::IterVarAttrNode']]],
['prefetch_5fscope',['prefetch_scope',['../namespacetvm_1_1tir_1_1attr.html#ac95fbd1c09a60b10c7a5d07f6c4b68a6',1,'tvm::tir::attr']]],
diff --git a/docs/reference/api/doxygen/search/all_14.js b/docs/reference/api/doxygen/search/all_14.js
index 80b3bccf2..18621986f 100644
--- a/docs/reference/api/doxygen/search/all_14.js
+++ b/docs/reference/api/doxygen/search/all_14.js
@@ -172,7 +172,7 @@ 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_1runtime_1_1NDArray.html#ad273c7bc59b73fb026fd64fc764cbebc',1,'tvm::runtime::NDArray::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()' [...]
+ ['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']]],
@@ -266,7 +266,7 @@ var searchData=
['spacegeneratornode',['SpaceGeneratorNode',['../classtvm_1_1meta__schedule_1_1SpaceGeneratorNode.html',1,'tvm::meta_schedule']]],
['spacegeneratorunion',['SpaceGeneratorUnion',['../classtvm_1_1meta__schedule_1_1SpaceGenerator.html#aa13f2244870b18f3e9788d41a400636e',1,'tvm::meta_schedule::SpaceGenerator']]],
['spacetobatchndattrs',['SpaceToBatchNDAttrs',['../structtvm_1_1relay_1_1SpaceToBatchNDAttrs.html',1,'tvm::relay']]],
- ['span',['Span',['../classtvm_1_1Span.html',1,'tvm::Span'],['../classtvm_1_1support_1_1Span.html',1,'tvm::support::Span< T, W >'],['../classtvm_1_1Span.html#a5216631b639e8c802263d87d3fe9e5f6',1,'tvm::Span::Span()'],['../classtvm_1_1support_1_1Span.html#a77653730a2542edf93b7c4413a72f3ec',1,'tvm::support::Span::Span(T *begin, int num_elements)'],['../classtvm_1_1support_1_1Span.html#a3c22dd06856e7029e7107adf38eb72f5',1,'tvm::support::Span::Span(T *begin, T *end)'],['../classtvm_1_1 [...]
+ ['span',['Span',['../classtvm_1_1Span.html',1,'tvm::Span'],['../classtvm_1_1support_1_1Span.html',1,'tvm::support::Span< T, W >'],['../classtvm_1_1AffineTypeNode.html#aa45c91e3c8ebcff609d10f6a921f3fa2',1,'tvm::AffineTypeNode::span()'],['../classtvm_1_1DiagnosticNode.html#af5469f228f87711ad8bd3f4f78f3bb54',1,'tvm::DiagnosticNode::span()'],['../classtvm_1_1DiagnosticBuilder.html#a52d9cc3cb33e655c5d82af47daa74c66',1,'tvm::DiagnosticBuilder::span()'],['../classtvm_1_1CompileError.htm [...]
['span_2eh',['span.h',['../ir_2span_8h.html',1,'(Global Namespace)'],['../support_2span_8h.html',1,'(Global Namespace)']]],
['spannode',['SpanNode',['../classtvm_1_1SpanNode.html',1,'tvm::SpanNode'],['../namespacetvm_1_1relay.html#a7d0fa6578e97d0d64b08865f94f04827',1,'tvm::relay::SpanNode()']]],
['sparse_5flhs',['sparse_lhs',['../structtvm_1_1relay_1_1SparseDenseAttrs.html#ae52d5465cb3421f342607abcc1cb1d5c',1,'tvm::relay::SparseDenseAttrs']]],
@@ -383,7 +383,7 @@ var searchData=
['store',['Store',['../classtvm_1_1tir_1_1Store.html',1,'tvm::tir::Store'],['../classtvm_1_1tir_1_1Store.html#a2c4278b8bcdae57ada2022ecc7c290c3',1,'tvm::tir::Store::Store()']]],
['store_5fpredicate',['store_predicate',['../classtvm_1_1te_1_1StageNode.html#a8f4ba7f2931b3541c12734af511600a7',1,'tvm::te::StageNode']]],
['storenode',['StoreNode',['../classtvm_1_1tir_1_1StoreNode.html',1,'tvm::tir']]],
- ['str',['str',['../classtvm_1_1TargetNode.html#a30cd67db46a9c4b098a8ba38fff22e26',1,'tvm::TargetNode::str()'],['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a789d7d73bd4d94612fa2a84c16b26b89',1,'tvm::script::printer::LiteralDoc::Str()']]],
+ ['str',['Str',['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a789d7d73bd4d94612fa2a84c16b26b89',1,'tvm::script::printer::LiteralDoc::Str()'],['../classtvm_1_1TargetNode.html#a30cd67db46a9c4b098a8ba38fff22e26',1,'tvm::TargetNode::str()']]],
['str2set',['Str2Set',['../namespacetvm_1_1topi.html#af01f6cc6b977801126083f0faffe252b',1,'tvm::topi']]],
['stream',['stream',['../classtvm_1_1ReprPrinter.html#a036409dcdcf6f0ac5c6d7d27ec60ed94',1,'tvm::ReprPrinter']]],
['streamsync',['StreamSync',['../classtvm_1_1runtime_1_1DeviceAPI.html#ac29b9295c432a87658392872c644864f',1,'tvm::runtime::DeviceAPI']]],
diff --git a/docs/reference/api/doxygen/search/all_15.js b/docs/reference/api/doxygen/search/all_15.js
index d6b0fa9d6..b2ec10dac 100644
--- a/docs/reference/api/doxygen/search/all_15.js
+++ b/docs/reference/api/doxygen/search/all_15.js
@@ -156,7 +156,7 @@ var searchData=
['touchtask',['TouchTask',['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#af6fa276674945d3432c129bdf9cea599',1,'tvm::meta_schedule::TaskSchedulerNode::TouchTask()'],['../classtvm_1_1meta__schedule_1_1PyTaskSchedulerNode.html#a7de09f81c8aceb580b43107f266e6b40',1,'tvm::meta_schedule::PyTaskSchedulerNode::TouchTask()']]],
['tovar',['ToVar',['../classtvm_1_1tir_1_1AnyNode.html#ae01ebbba2378afb6509a22de97f8fb30',1,'tvm::tir::AnyNode']]],
['tparent',['TParent',['../classtvm_1_1OpAttrMap.html#a316480ca7450209650fc1a62f7ce4a14',1,'tvm::OpAttrMap::TParent()'],['../classtvm_1_1TargetKindAttrMap.html#a37eb6bfb0d881cf897147b17ff7d3265',1,'tvm::TargetKindAttrMap::TParent()']]],
- ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html',1,'tvm::tir::Trace'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29',1,'tvm::meta_schedule::TuningRecordNode::trace()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb [...]
+ ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html',1,'tvm::tir::Trace'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array< Instruction > insts, Map< Instruction, ObjectRef > decisions)'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29',1,'tvm::meta_schedule::TuningRecordNode::tra [...]
['trace_2eh',['trace.h',['../trace_8h.html',1,'']]],
['traced',['Traced',['../classtvm_1_1tir_1_1Schedule.html#a295d432b86621101f67b20fadb367b91',1,'tvm::tir::Schedule']]],
['traced_5fobject_2eh',['traced_object.h',['../traced__object_8h.html',1,'']]],
diff --git a/docs/reference/api/doxygen/search/all_16.js b/docs/reference/api/doxygen/search/all_16.js
index c2f930cf4..cea508f3d 100644
--- a/docs/reference/api/doxygen/search/all_16.js
+++ b/docs/reference/api/doxygen/search/all_16.js
@@ -24,9 +24,9 @@ var searchData=
['unknownattributeaccesspathnode',['UnknownAttributeAccessPathNode',['../classtvm_1_1UnknownAttributeAccessPathNode.html',1,'tvm::UnknownAttributeAccessPathNode'],['../classtvm_1_1UnknownAttributeAccessPathNode.html#a1882e9e591466a2785acc761dc63d56e',1,'tvm::UnknownAttributeAccessPathNode::UnknownAttributeAccessPathNode()']]],
['unmatchedcases',['UnmatchedCases',['../namespacetvm_1_1relay.html#aa3a8cace40f8056fd6412f39c3eaa605',1,'tvm::relay']]],
['unravel_5findex',['unravel_index',['../namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e',1,'tvm::topi']]],
- ['unroll',['Unroll',['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()'],['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()']]],
+ ['unroll',['unroll',['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()']]],
['unrollloop',['UnrollLoop',['../namespacetvm_1_1tir_1_1transform.html#ab2f279e91071fa96a1edb24fa004ea6a',1,'tvm::tir::transform']]],
- ['update',['update',['../classtvm_1_1te_1_1ScanOpNode.html#ace2bf7e43cd4197324ec6363626fc60a',1,'tvm::te::ScanOpNode::update()'],['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::a [...]
+ ['update',['Update',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::arith::RewriteSimplifier::Update()'],['../classtvm_1_1arith_1_1CanonicalSimplifier.html#a790c032e12c7d93e9e940 [...]
['update_5ffunc',['update_func',['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#ade9364c152a36501d4f24fa4f0111519',1,'tvm::auto_scheduler::PythonBasedModelNode']]],
['updatecostmodel',['UpdateCostModel',['../classtvm_1_1meta__schedule_1_1MeasureCallback.html#afdf5503c6e6f53767de132d91a7b53f9',1,'tvm::meta_schedule::MeasureCallback']]],
['updateiters',['UpdateIters',['../classtvm_1_1auto__scheduler_1_1AttachMap.html#ab45b991ef2bcfb1bc191601aac42e778',1,'tvm::auto_scheduler::AttachMap']]],
diff --git a/docs/reference/api/doxygen/search/all_18.js b/docs/reference/api/doxygen/search/all_18.js
index ec7a0a551..37489c02b 100644
--- a/docs/reference/api/doxygen/search/all_18.js
+++ b/docs/reference/api/doxygen/search/all_18.js
@@ -33,7 +33,7 @@ var searchData=
['withframe',['WithFrame',['../classtvm_1_1script_1_1printer_1_1IRDocsifierNode.html#aeb321e859e30f7a3917a4ca8db71d472',1,'tvm::script::printer::IRDocsifierNode']]],
['withhost',['WithHost',['../classtvm_1_1Target.html#a509ce63995f082c80742ea5ca6ac112f',1,'tvm::Target']]],
['withoutattr',['WithoutAttr',['../namespacetvm.html#a7e2bc626db8be997b1562c79df3d9e11',1,'tvm']]],
- ['workload',['Workload',['../classtvm_1_1meta__schedule_1_1Workload.html',1,'tvm::meta_schedule::Workload'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a42c87f1ec62dae6806c3fe9629c5e7f0',1,'tvm::meta_schedule::TuningRecordNode::workload()'],['../classtvm_1_1meta__schedule_1_1Workload.html#a21ccf9c956b82d50a2579f1c0f592fd0',1,'tvm::meta_schedule::Workload::Workload(IRModule mod)'],['../classtvm_1_1meta__schedule_1_1Workload.html#a8880877517679c82ae63520e28d5e1d8',1,'tvm::me [...]
+ ['workload',['Workload',['../classtvm_1_1meta__schedule_1_1Workload.html',1,'tvm::meta_schedule::Workload'],['../classtvm_1_1meta__schedule_1_1Workload.html#a21ccf9c956b82d50a2579f1c0f592fd0',1,'tvm::meta_schedule::Workload::Workload(IRModule mod)'],['../classtvm_1_1meta__schedule_1_1Workload.html#a8880877517679c82ae63520e28d5e1d8',1,'tvm::meta_schedule::Workload::Workload(IRModule mod, THashCode shash)'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a42c87f1ec62dae6806c3fe9 [...]
['workload_5fkey',['workload_key',['../classtvm_1_1auto__scheduler_1_1SearchTaskNode.html#a20045d677ba2bc5c5ce461e78543b3e2',1,'tvm::auto_scheduler::SearchTaskNode']]],
['workloadequal',['WorkloadEqual',['../structtvm_1_1meta__schedule_1_1WorkloadEqual.html',1,'tvm::meta_schedule']]],
['workloadhash',['WorkloadHash',['../structtvm_1_1meta__schedule_1_1WorkloadHash.html',1,'tvm::meta_schedule']]],
diff --git a/docs/reference/api/doxygen/search/all_8.js b/docs/reference/api/doxygen/search/all_8.js
index 1d0057faf..4005caf24 100644
--- a/docs/reference/api/doxygen/search/all_8.js
+++ b/docs/reference/api/doxygen/search/all_8.js
@@ -74,6 +74,7 @@ var searchData=
['getiopoolallocations',['GetIOPoolAllocations',['../namespacetvm_1_1tir_1_1usmp.html#af09b2e5d53a727e24e1322834b71b67f',1,'tvm::tir::usmp']]],
['getkeys',['GetKeys',['../classtvm_1_1TargetNode.html#abd05b2c258974b13af1192c911ccb12b',1,'tvm::TargetNode']]],
['getlastframe',['GetLastFrame',['../classtvm_1_1script_1_1ir__builder_1_1IRBuilderNode.html#a8f8071bc13ae7d04ab49111ecc472027',1,'tvm::script::ir_builder::IRBuilderNode']]],
+ ['getlateboundconstants',['GetLateBoundConstants',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#ad0dd5c8b70a9c2aff7e0a0517de53e0c',1,'tvm::runtime::vm::Executable']]],
['getlib',['GetLib',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#aabfeb049c4a50df7b204b34f56b31567',1,'tvm::runtime::vm::Executable']]],
['getlibs',['GetLibs',['../classtvm_1_1TargetNode.html#a1bd600905c1a4469726184adbc9087b0',1,'tvm::TargetNode']]],
['getline',['GetLine',['../classtvm_1_1parser_1_1Source.html#a5b1d51f8eac2d6cacb8b771f3f63d24a',1,'tvm::parser::Source']]],
diff --git a/docs/reference/api/doxygen/search/all_d.js b/docs/reference/api/doxygen/search/all_d.js
index eabdd2355..5dfab61f3 100644
--- a/docs/reference/api/doxygen/search/all_d.js
+++ b/docs/reference/api/doxygen/search/all_d.js
@@ -77,6 +77,7 @@ var searchData=
['loadfromfile',['LoadFromFile',['../classtvm_1_1runtime_1_1Module.html#a1927112ff253c1a6150238257cc9d5dd',1,'tvm::runtime::Module']]],
['loadjson',['LoadJSON',['../namespacetvm.html#afa0a9bdf3997ef4fad45b19fb1a655cd',1,'tvm']]],
['loadlateboundconstantsfromfile',['LoadLateBoundConstantsFromFile',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#a09a77db67e7e8a01be05f844d3f3dd53',1,'tvm::runtime::vm::Executable']]],
+ ['loadlateboundconstantsfrommap',['LoadLateBoundConstantsFromMap',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#aa1e52496153fc99ed66db7ca54e1a3fc',1,'tvm::runtime::vm::Executable']]],
['loadlateboundconstantsfromstream',['LoadLateBoundConstantsFromStream',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#a2c01fd2724008842e2fff9b7cf6eab33',1,'tvm::runtime::vm::Executable']]],
['loadnode',['LoadNode',['../classtvm_1_1tir_1_1LoadNode.html',1,'tvm::tir']]],
['loadscalarint',['LoadScalarInt',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a27fc0a1ece314cdd8478a5f68cdd3954',1,'tvm::runtime::vm::VirtualMachine']]],
diff --git a/docs/reference/api/doxygen/search/all_e.js b/docs/reference/api/doxygen/search/all_e.js
index ffc7552f7..5cc38f851 100644
--- a/docs/reference/api/doxygen/search/all_e.js
+++ b/docs/reference/api/doxygen/search/all_e.js
@@ -70,7 +70,7 @@ var searchData=
['matmulattrs',['MatmulAttrs',['../structtvm_1_1relay_1_1MatmulAttrs.html',1,'tvm::relay']]],
['matrix_5fset_5fdiag',['matrix_set_diag',['../namespacetvm_1_1topi.html#aead477c6c9d4f4589d22b8acff82040c',1,'tvm::topi']]],
['matrixsetdiagattrs',['MatrixSetDiagAttrs',['../structtvm_1_1relay_1_1MatrixSetDiagAttrs.html',1,'tvm::relay']]],
- ['max',['Max',['../classtvm_1_1tir_1_1Max.html',1,'tvm::tir::Max'],['../classtvm_1_1tir_1_1Max.html#a7dff11b4dea01bfc7a03eacd077f0729',1,'tvm::tir::Max::Max()'],['../classtvm_1_1arith_1_1IntSet.html#ac215840d3e9fb2817f1e5648e31317c5',1,'tvm::arith::IntSet::max()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#a2c5ea87b1155aa7810e0beb3b69b955b',1,'tvm::support::LinearCongruentialEngine::max()'],['../namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb',1,'tvm::max(PrimExpr a, [...]
+ ['max',['Max',['../classtvm_1_1tir_1_1Max.html',1,'tvm::tir::Max'],['../classtvm_1_1arith_1_1IntSet.html#ac215840d3e9fb2817f1e5648e31317c5',1,'tvm::arith::IntSet::max()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#a2c5ea87b1155aa7810e0beb3b69b955b',1,'tvm::support::LinearCongruentialEngine::max()'],['../classtvm_1_1tir_1_1Max.html#a7dff11b4dea01bfc7a03eacd077f0729',1,'tvm::tir::Max::Max()'],['../namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb',1,'tvm::max(PrimExpr a, [...]
['max_5fcontinuous_5ferror',['max_continuous_error',['../classtvm_1_1auto__scheduler_1_1ProgramMeasurerNode.html#abdc38da91bcdf77be765c1e3d5af3648',1,'tvm::auto_scheduler::ProgramMeasurerNode']]],
['max_5fdisplacement',['max_displacement',['../structtvm_1_1relay_1_1CorrelationAttrs.html#ad1d16e2ba537736c8baee2553e1e32bf',1,'tvm::relay::CorrelationAttrs']]],
['max_5ffunctions',['max_functions',['../structTVMMutableFuncRegistry.html#a41745f8e0f73f8e4fb2074f5b154b49c',1,'TVMMutableFuncRegistry']]],
@@ -201,7 +201,7 @@ var searchData=
['modularset',['ModularSet',['../classtvm_1_1arith_1_1ModularSet.html',1,'tvm::arith::ModularSet'],['../classtvm_1_1arith_1_1ModularSet.html#a9f54896d98169246c6a24cc338fde500',1,'tvm::arith::ModularSet::ModularSet()']]],
['modularsetanalyzer',['ModularSetAnalyzer',['../classtvm_1_1arith_1_1ModularSetAnalyzer.html',1,'tvm::arith']]],
['modularsetnode',['ModularSetNode',['../classtvm_1_1arith_1_1ModularSetNode.html',1,'tvm::arith']]],
- ['module',['Module',['../classtvm_1_1runtime_1_1Module.html',1,'tvm::runtime::Module'],['../classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d',1,'tvm::runtime::ModuleNode::Module()'],['../classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9',1,'tvm::runtime::Module::Module()'],['../classtvm_1_1runtime_1_1Module.html#abd1380b3f813c2b6acefca3aaef425f4',1,'tvm::runtime::Module::Module(ObjectPtr< Object > n)'],['../classtvm_1_1DiagnosticContextN [...]
+ ['module',['Module',['../classtvm_1_1runtime_1_1Module.html',1,'tvm::runtime::Module'],['../classtvm_1_1DiagnosticContextNode.html#adea7e38a6e47cbab7fb5639f208aa536',1,'tvm::DiagnosticContextNode::module()'],['../classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d',1,'tvm::runtime::ModuleNode::Module()'],['../classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9',1,'tvm::runtime::Module::Module()'],['../classtvm_1_1runtime_1_1Module.html#abd1380b3f81 [...]
['module_2eh',['module.h',['../ir_2module_8h.html',1,'(Global Namespace)'],['../runtime_2crt_2module_8h.html',1,'(Global Namespace)'],['../runtime_2module_8h.html',1,'(Global Namespace)']]],
['module_5fhandle',['module_handle',['../structTVMAotExecutor.html#a0d4158663d39f79d88d2bc0355c9f1eb',1,'TVMAotExecutor']]],
['moduleinternal',['ModuleInternal',['../classtvm_1_1runtime_1_1ModuleNode.html#a2b490c1acecd166b5824e4e96f17c64e',1,'tvm::runtime::ModuleNode']]],
diff --git a/docs/reference/api/doxygen/search/functions_10.js b/docs/reference/api/doxygen/search/functions_10.js
index c7a6df2c2..a4526aba3 100644
--- a/docs/reference/api/doxygen/search/functions_10.js
+++ b/docs/reference/api/doxygen/search/functions_10.js
@@ -9,7 +9,7 @@ var searchData=
['packimportstollvm',['PackImportsToLLVM',['../namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6',1,'tvm::codegen']]],
['pad',['pad',['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElementWise, std::string pad_mode="constant", const Array< PrimExpr > *dyn_output_shape=nullptr)'],['../namespacetvm_1_1topi [...]
['pagememorymanagercreate',['PageMemoryManagerCreate',['../page__allocator_8h.html#a720dbc7474ac13b93fafb974cfc20bc7',1,'page_allocator.h']]],
- ['parallel',['parallel',['../classtvm_1_1auto__scheduler_1_1State.html#a2376f0180bc5b5dd4b456f2a75d4a366',1,'tvm::auto_scheduler::State::parallel()'],['../classtvm_1_1te_1_1Stage.html#a60a6be10a1a96cb594c1399efabafef3',1,'tvm::te::Stage::parallel()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a553dc17c0b49b175cd16881c81b6c789',1,'tvm::tir::ScheduleNode::Parallel()']]],
+ ['parallel',['Parallel',['../classtvm_1_1tir_1_1ScheduleNode.html#a553dc17c0b49b175cd16881c81b6c789',1,'tvm::tir::ScheduleNode::Parallel()'],['../classtvm_1_1auto__scheduler_1_1State.html#a2376f0180bc5b5dd4b456f2a75d4a366',1,'tvm::auto_scheduler::State::parallel()'],['../classtvm_1_1te_1_1Stage.html#a60a6be10a1a96cb594c1399efabafef3',1,'tvm::te::Stage::parallel()']]],
['parallel_5ffor',['parallel_for',['../namespacetvm_1_1support.html#a8bf1225e8bb1db575578ca2d645fb23c',1,'tvm::support']]],
['parallel_5ffor_5fdynamic',['parallel_for_dynamic',['../namespacetvm_1_1support.html#afe4271363c794f1644ce7af5c2266530',1,'tvm::support']]],
['parallelizevectorizeunroll',['ParallelizeVectorizeUnroll',['../classtvm_1_1meta__schedule_1_1ScheduleRule.html#a0ef9b604081db7a8bf960f3fbfd3a804',1,'tvm::meta_schedule::ScheduleRule']]],
@@ -69,7 +69,7 @@ var searchData=
['pragmastep',['PragmaStep',['../classtvm_1_1auto__scheduler_1_1PragmaStep.html#a9f3ec96f3e561a14d8d9235c4d46e2eb',1,'tvm::auto_scheduler::PragmaStep::PragmaStep(int stage_id, int iter_id, String pragma_type)'],['../classtvm_1_1auto__scheduler_1_1PragmaStep.html#a7692c2a9934af1f36b218840034a88d5',1,'tvm::auto_scheduler::PragmaStep::PragmaStep(dmlc::JSONReader *reader)']]],
['predict',['Predict',['../classtvm_1_1auto__scheduler_1_1CostModelNode.html#aa337ec72401a957a68b6eb4a96472a2c',1,'tvm::auto_scheduler::CostModelNode::Predict()'],['../classtvm_1_1auto__scheduler_1_1RandomModelNode.html#a09f1d81fd9d9f93fca5f2008ab6054ba',1,'tvm::auto_scheduler::RandomModelNode::Predict()'],['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#af16befe722e718fea23727469fecea1c',1,'tvm::auto_scheduler::PythonBasedModelNode::Predict()'],['../classtvm_1_1meta__sche [...]
['predictstages',['PredictStages',['../classtvm_1_1auto__scheduler_1_1CostModelNode.html#a213222251099444874698d2e9ff18adc',1,'tvm::auto_scheduler::CostModelNode::PredictStages()'],['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#a1f9975c4bdd61793b806663a61a9a703',1,'tvm::auto_scheduler::PythonBasedModelNode::PredictStages()']]],
- ['prefetch',['Prefetch',['../classtvm_1_1tir_1_1Prefetch.html#af462f85dad4268685e3113b6b009d1b2',1,'tvm::tir::Prefetch::Prefetch()'],['../classtvm_1_1te_1_1Stage.html#a611327890918fb641a8e65396ab9c5f6',1,'tvm::te::Stage::prefetch()'],['../namespacetvm_1_1tir_1_1builtin.html#a543f1fc334d2bc830add972895a03f17',1,'tvm::tir::builtin::prefetch()']]],
+ ['prefetch',['prefetch',['../classtvm_1_1te_1_1Stage.html#a611327890918fb641a8e65396ab9c5f6',1,'tvm::te::Stage::prefetch()'],['../classtvm_1_1tir_1_1Prefetch.html#af462f85dad4268685e3113b6b009d1b2',1,'tvm::tir::Prefetch::Prefetch()'],['../namespacetvm_1_1tir_1_1builtin.html#a543f1fc334d2bc830add972895a03f17',1,'tvm::tir::builtin::prefetch()']]],
['prefetchnode',['PrefetchNode',['../classtvm_1_1tir_1_1PrefetchNode.html#acaaa5e89462c7edf3019df4283ec74db',1,'tvm::tir::PrefetchNode::PrefetchNode()=default'],['../classtvm_1_1tir_1_1PrefetchNode.html#a73ef244c364b9c7efaee36e6bec746e7',1,'tvm::tir::PrefetchNode::PrefetchNode(Buffer buffer, Array< Range > bounds, Span span=Span())']]],
['preloadmeasuredstates',['PreloadMeasuredStates',['../classtvm_1_1auto__scheduler_1_1PreloadMeasuredStates.html#a67daf1ccd25a208fdf8d001f9a31d86b',1,'tvm::auto_scheduler::PreloadMeasuredStates::PreloadMeasuredStates()'],['../classtvm_1_1auto__scheduler_1_1SearchPolicyNode.html#abc2529d0b1cd485876e48037dd19dde1',1,'tvm::auto_scheduler::SearchPolicyNode::PreloadMeasuredStates()']]],
['prelu',['prelu',['../namespacetvm_1_1topi.html#a315c34bbe2bf1be4c778acae08c906fc',1,'tvm::topi']]],
diff --git a/docs/reference/api/doxygen/search/functions_13.js b/docs/reference/api/doxygen/search/functions_13.js
index a31666255..92378c79f 100644
--- a/docs/reference/api/doxygen/search/functions_13.js
+++ b/docs/reference/api/doxygen/search/functions_13.js
@@ -104,7 +104,7 @@ 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_1runtime_1_1NDArray.html#ad273c7bc59b73fb026fd64fc764cbebc',1,'tvm::runtime::NDArray::Shape()'],['../classtvm_1_1runtime_1_1metadata_1_1TensorInfoNode.html#a5ddcd966b82c4df89084dbdf92d3108e',1,'tvm::runtime::metadata::TensorInfoNode::shape()'],['../namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1',1,'tvm::topi::shape()']]],
+ ['shape',['shape',['../classtvm_1_1runtime_1_1metadata_1_1TensorInfoNode.html#a5ddcd966b82c4df89084dbdf92d3108e',1,'tvm::runtime::metadata::TensorInfoNode::shape()'],['../classtvm_1_1runtime_1_1NDArray.html#ad273c7bc59b73fb026fd64fc764cbebc',1,'tvm::runtime::NDArray::Shape()'],['../namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1',1,'tvm::topi::shape()']]],
['shapediv',['shapediv',['../namespacetvm.html#a15f25703cfce73c75cb4cd33c74ea8f0',1,'tvm']]],
['shapeindex',['ShapeIndex',['../classtvm_1_1runtime_1_1DataType.html#a04f0e069017af3f0da47bc0c1fd80916',1,'tvm::runtime::DataType']]],
['shapeof',['ShapeOf',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a5f278c637580946bc06b020f5852e44a',1,'tvm::runtime::vm::Instruction']]],
@@ -194,7 +194,7 @@ var searchData=
['storageflatten',['StorageFlatten',['../namespacetvm_1_1tir_1_1transform.html#a778d3e1efecdff97e7bcf0e6a5406e61',1,'tvm::tir::transform']]],
['storagerewrite',['StorageRewrite',['../namespacetvm_1_1tir_1_1transform.html#abe87b271e2c20e0ad901697f33c01d2c',1,'tvm::tir::transform']]],
['store',['Store',['../classtvm_1_1tir_1_1Store.html#a2c4278b8bcdae57ada2022ecc7c290c3',1,'tvm::tir::Store']]],
- ['str',['str',['../classtvm_1_1TargetNode.html#a30cd67db46a9c4b098a8ba38fff22e26',1,'tvm::TargetNode::str()'],['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a789d7d73bd4d94612fa2a84c16b26b89',1,'tvm::script::printer::LiteralDoc::Str()']]],
+ ['str',['Str',['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a789d7d73bd4d94612fa2a84c16b26b89',1,'tvm::script::printer::LiteralDoc::Str()'],['../classtvm_1_1TargetNode.html#a30cd67db46a9c4b098a8ba38fff22e26',1,'tvm::TargetNode::str()']]],
['str2set',['Str2Set',['../namespacetvm_1_1topi.html#af01f6cc6b977801126083f0faffe252b',1,'tvm::topi']]],
['streamsync',['StreamSync',['../classtvm_1_1runtime_1_1DeviceAPI.html#ac29b9295c432a87658392872c644864f',1,'tvm::runtime::DeviceAPI']]],
['strided_5fslice',['strided_slice',['../namespacetvm_1_1topi.html#a208e90d4a8db8cf2c7d77b4460f7df70',1,'tvm::topi']]],
diff --git a/docs/reference/api/doxygen/search/functions_14.js b/docs/reference/api/doxygen/search/functions_14.js
index 7e6f92995..9e9099ec7 100644
--- a/docs/reference/api/doxygen/search/functions_14.js
+++ b/docs/reference/api/doxygen/search/functions_14.js
@@ -51,7 +51,7 @@ var searchData=
['totupletype',['ToTupleType',['../namespacetvm_1_1relay.html#ae6757a008816e31cce4109e8dfc2bc16',1,'tvm::relay']]],
['touchtask',['TouchTask',['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#af6fa276674945d3432c129bdf9cea599',1,'tvm::meta_schedule::TaskSchedulerNode::TouchTask()'],['../classtvm_1_1meta__schedule_1_1PyTaskSchedulerNode.html#a7de09f81c8aceb580b43107f266e6b40',1,'tvm::meta_schedule::PyTaskSchedulerNode::TouchTask()']]],
['tovar',['ToVar',['../classtvm_1_1tir_1_1AnyNode.html#ae01ebbba2378afb6509a22de97f8fb30',1,'tvm::tir::AnyNode']]],
- ['trace',['trace',['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array< Instruction > insts, Map< Instruction, ObjectRef > decisions)']]],
+ ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array< Instruction > insts, Map< Instruction, ObjectRef > decisions)'],['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()']]],
['traced',['Traced',['../classtvm_1_1tir_1_1Schedule.html#a295d432b86621101f67b20fadb367b91',1,'tvm::tir::Schedule']]],
['tracedarray',['TracedArray',['../classtvm_1_1TracedArray.html#a7b1ab76aea02b3357239cbe6b521bc39',1,'tvm::TracedArray']]],
['tracedarrayiterator',['TracedArrayIterator',['../classtvm_1_1TracedArrayIterator.html#a684a4dfb9a548bff64120cf40822a3b9',1,'tvm::TracedArrayIterator']]],
diff --git a/docs/reference/api/doxygen/search/functions_15.js b/docs/reference/api/doxygen/search/functions_15.js
index bbc21e6f4..fd8b30131 100644
--- a/docs/reference/api/doxygen/search/functions_15.js
+++ b/docs/reference/api/doxygen/search/functions_15.js
@@ -17,7 +17,7 @@ var searchData=
['unknownattributeaccesspathnode',['UnknownAttributeAccessPathNode',['../classtvm_1_1UnknownAttributeAccessPathNode.html#a1882e9e591466a2785acc761dc63d56e',1,'tvm::UnknownAttributeAccessPathNode']]],
['unmatchedcases',['UnmatchedCases',['../namespacetvm_1_1relay.html#aa3a8cace40f8056fd6412f39c3eaa605',1,'tvm::relay']]],
['unravel_5findex',['unravel_index',['../namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e',1,'tvm::topi']]],
- ['unroll',['Unroll',['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()'],['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()']]],
+ ['unroll',['unroll',['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()']]],
['unrollloop',['UnrollLoop',['../namespacetvm_1_1tir_1_1transform.html#ab2f279e91071fa96a1edb24fa004ea6a',1,'tvm::tir::transform']]],
['update',['Update',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::arith::RewriteSimplifier::Update()'],['../classtvm_1_1arith_1_1CanonicalSimplifier.html#a790c032e12c7d93e9e940 [...]
['updatecostmodel',['UpdateCostModel',['../classtvm_1_1meta__schedule_1_1MeasureCallback.html#afdf5503c6e6f53767de132d91a7b53f9',1,'tvm::meta_schedule::MeasureCallback']]],
diff --git a/docs/reference/api/doxygen/search/functions_7.js b/docs/reference/api/doxygen/search/functions_7.js
index 3da1b6b6f..05e51aa85 100644
--- a/docs/reference/api/doxygen/search/functions_7.js
+++ b/docs/reference/api/doxygen/search/functions_7.js
@@ -65,6 +65,7 @@ var searchData=
['getiopoolallocations',['GetIOPoolAllocations',['../namespacetvm_1_1tir_1_1usmp.html#af09b2e5d53a727e24e1322834b71b67f',1,'tvm::tir::usmp']]],
['getkeys',['GetKeys',['../classtvm_1_1TargetNode.html#abd05b2c258974b13af1192c911ccb12b',1,'tvm::TargetNode']]],
['getlastframe',['GetLastFrame',['../classtvm_1_1script_1_1ir__builder_1_1IRBuilderNode.html#a8f8071bc13ae7d04ab49111ecc472027',1,'tvm::script::ir_builder::IRBuilderNode']]],
+ ['getlateboundconstants',['GetLateBoundConstants',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#ad0dd5c8b70a9c2aff7e0a0517de53e0c',1,'tvm::runtime::vm::Executable']]],
['getlib',['GetLib',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#aabfeb049c4a50df7b204b34f56b31567',1,'tvm::runtime::vm::Executable']]],
['getlibs',['GetLibs',['../classtvm_1_1TargetNode.html#a1bd600905c1a4469726184adbc9087b0',1,'tvm::TargetNode']]],
['getline',['GetLine',['../classtvm_1_1parser_1_1Source.html#a5b1d51f8eac2d6cacb8b771f3f63d24a',1,'tvm::parser::Source']]],
diff --git a/docs/reference/api/doxygen/search/functions_c.js b/docs/reference/api/doxygen/search/functions_c.js
index d277010fb..ffd239773 100644
--- a/docs/reference/api/doxygen/search/functions_c.js
+++ b/docs/reference/api/doxygen/search/functions_c.js
@@ -44,6 +44,7 @@ var searchData=
['loadfromfile',['LoadFromFile',['../classtvm_1_1runtime_1_1Module.html#a1927112ff253c1a6150238257cc9d5dd',1,'tvm::runtime::Module']]],
['loadjson',['LoadJSON',['../namespacetvm.html#afa0a9bdf3997ef4fad45b19fb1a655cd',1,'tvm']]],
['loadlateboundconstantsfromfile',['LoadLateBoundConstantsFromFile',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#a09a77db67e7e8a01be05f844d3f3dd53',1,'tvm::runtime::vm::Executable']]],
+ ['loadlateboundconstantsfrommap',['LoadLateBoundConstantsFromMap',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#aa1e52496153fc99ed66db7ca54e1a3fc',1,'tvm::runtime::vm::Executable']]],
['loadlateboundconstantsfromstream',['LoadLateBoundConstantsFromStream',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#a2c01fd2724008842e2fff9b7cf6eab33',1,'tvm::runtime::vm::Executable']]],
['loadscalarint',['LoadScalarInt',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a27fc0a1ece314cdd8478a5f68cdd3954',1,'tvm::runtime::vm::VirtualMachine']]],
['localbuilder',['LocalBuilder',['../classtvm_1_1auto__scheduler_1_1LocalBuilder.html#aedf9319cffd9a630258ed66dcbea3739',1,'tvm::auto_scheduler::LocalBuilder']]],
diff --git a/docs/reference/api/doxygen/search/functions_d.js b/docs/reference/api/doxygen/search/functions_d.js
index 860ee6399..8b4051298 100644
--- a/docs/reference/api/doxygen/search/functions_d.js
+++ b/docs/reference/api/doxygen/search/functions_d.js
@@ -35,7 +35,7 @@ var searchData=
['matchrange',['MatchRange',['../classtvm_1_1arith_1_1IntSet.html#a2f2999336fbba4f436b66bdddce5c57a',1,'tvm::arith::IntSet']]],
['matmul',['matmul',['../namespacetvm_1_1topi.html#adae7dcb7e951109ba72192202d182994',1,'tvm::topi']]],
['matrix_5fset_5fdiag',['matrix_set_diag',['../namespacetvm_1_1topi.html#aead477c6c9d4f4589d22b8acff82040c',1,'tvm::topi']]],
- ['max',['Max',['../classtvm_1_1tir_1_1Max.html#a7dff11b4dea01bfc7a03eacd077f0729',1,'tvm::tir::Max::Max()'],['../classtvm_1_1arith_1_1IntSet.html#ac215840d3e9fb2817f1e5648e31317c5',1,'tvm::arith::IntSet::max()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#a2c5ea87b1155aa7810e0beb3b69b955b',1,'tvm::support::LinearCongruentialEngine::max()'],['../namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb',1,'tvm::max(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.ht [...]
+ ['max',['max',['../classtvm_1_1arith_1_1IntSet.html#ac215840d3e9fb2817f1e5648e31317c5',1,'tvm::arith::IntSet::max()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#a2c5ea87b1155aa7810e0beb3b69b955b',1,'tvm::support::LinearCongruentialEngine::max()'],['../classtvm_1_1tir_1_1Max.html#a7dff11b4dea01bfc7a03eacd077f0729',1,'tvm::tir::Max::Max()'],['../namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb',1,'tvm::max(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.ht [...]
['max_5fvalue',['max_value',['../namespacetvm.html#a4f1398024c0af23699447ef910b654b8',1,'tvm']]],
['maxconcurrency',['MaxConcurrency',['../namespacetvm_1_1runtime_1_1threading.html#af8c1c389a74e67bcc3680555288219f8',1,'tvm::runtime::threading']]],
['maximum',['maximum',['../namespacetvm_1_1topi.html#afd64bc3e27dfc97002d3add5d7ce4174',1,'tvm::topi::maximum(const tvm::PrimExpr &a, const tvm::PrimExpr &b)'],['../namespacetvm_1_1topi.html#a5338e9297463bc745027fca67daa2ebb',1,'tvm::topi::maximum(const tvm::te::Tensor &A, const tvm::te::Tensor &B, std::string name="T_" "maximum", std::string tag=kBroadcast)'],['../namespacetvm_1_1topi.html#a4076a8d6a2b243c548d741e9f6bcfe69',1,'tvm::topi::maximum(con [...]
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index ec7167b75..a5de10458 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 806ac54c1..4397c8f89 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/32f9a5f4d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 b2e12ac0c..101d3242d 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/32f9a5f4d/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 7bdf8e463..8a3eedfa3 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/32f9a5f4d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 a0a266c5b..099d1ee96 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/32f9a5f4d/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 618397e74..6331ba5d8 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/32f9a5f4d/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 2b535fc5a..e9d21497c 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/32f9a5f4d/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 3dc214f2f..0d59acec2 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/32f9a5f4d/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 6b2b3702e..d6dbe7464 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/32f9a5f4d/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/32f9a5f4d/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 8a53bbd8d..3fb8f1c10 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/32f9a5f4d/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 e83362dce..81fb07f56 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/32f9a5f4d/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 cd6ce57ef..673861856 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/32f9a5f4d/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 3a779c5c0..03e90d27a 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/32f9a5f4d/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 9a49ec479..e305fd2c7 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/32f9a5f4d/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 cf6487407..040e29e2a 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/32f9a5f4d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 25611077d..d05c5a475 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/32f9a5f4d/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 91040834f..4d00d1e37 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/32f9a5f4d/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 e5c80c3b6..1ca3e2229 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/32f9a5f4d/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 b62f69214..2b25dae32 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/32f9a5f4d/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 737d13e46..3665025a2 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/32f9a5f4d/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 e5c6e2033..416539df9 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/32f9a5f4d/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 b039cd935..a04456f38 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/32f9a5f4d/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/32f9a5f4d/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 713b3aee7..9a7ba4f49 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/32f9a5f4d/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 fcc8a410d..88c7a357c 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/32f9a5f4d/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 2f8704760..98dddf218 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/32f9a5f4d/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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/32f9a5f4d/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/e814f798e/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 b7de15df0..0e9b5ba7c 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index f5f3391ca..e4dd94cb4 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:22.198</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.304</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:22.191</p></td>
+<td><p>00:21.297</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 42b5997fa..252cee99d 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 23.86s!
+resnet18_v1 inference graph built in 23.02s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index a715f49af..543086bac 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.62s!
+yolov3-tiny inference graph built in 16.16s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 31dc8299a..0cc75ff95 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:33.653</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:32.597</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:49.474</p></td>
+<td><p>00:49.153</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:44.179</p></td>
+<td><p>00:43.444</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 3573723d3..e72c6980d 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.259</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.317</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.861</p></td>
+<td><p>00:02.907</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.398</p></td>
+<td><p>00:00.409</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 6a7d19266..db9e510d9 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.708</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.746</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.374</p></td>
+<td><p>00:00.398</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.334</p></td>
+<td><p>00:00.347</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 4acaad5ca..3ced37936 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -565,7 +565,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.262 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.447 ms
</pre></div>
</div>
</div>
@@ -640,7 +640,6 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.533 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 7f42826ab..db1f5c1c5 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.33/10.33 result: MeasureResult(costs=(0.0259806908,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.553368091583252, timestamp=1662044930.8355842) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.95/10.33 result: MeasureResult(costs=(0.0909442286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.607630968093872, timestamp=1662044932.4553208) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0227978484,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5645833015441895, timestamp=1662044933.524316) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.86/11.77 result: MeasureResult(costs=(0.1443764272,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.426344394683838, timestamp=1662044936.5437012) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.65/11.77 result: MeasureResult(costs=(0.073616742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3122961521148682, timestamp=1662044938.5254374) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.75/11.77 result: MeasureResult(costs=(0.15349440939999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.635594367980957, timestamp=1662044941.2042146) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.81/11.77 result: MeasureResult(costs=(0.330520309,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.405975818634033, timestamp=1662044946.6555026) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.38/11.77 result: MeasureResult(costs=(0.025863171,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5585572719573975, timestamp=1662044947.2317955) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.95/11.77 result: MeasureResult(costs=(0.1379159984,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3240528106689453, timestamp=1662044949.6758037) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.52/11.77 result: MeasureResult(costs=(0.1063534746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.805710792541504, timestamp=1662044951.5397818) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.65/9.65 result: MeasureResult(costs=(0.027818264399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5809295177459717, timestamp=1662052883.3688154) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.25/9.65 result: MeasureResult(costs=(0.119499149,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.064157485961914, timestamp=1662052885.9779427) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.81/11.81 result: MeasureResult(costs=(0.02273791,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6039459705352783, timestamp=1662052886.5468912) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.64/11.81 result: MeasureResult(costs=(0.1637648022,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7406458854675293, timestamp=1662052889.8632522) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.62/11.81 result: MeasureResult(costs=(0.074074002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.322547435760498, timestamp=1662052891.316292) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.61/11.81 result: MeasureResult(costs=(0.166580006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7907514572143555, timestamp=1662052894.6801717) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.81/11.81 result: MeasureResult(costs=(0.3312716924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.42108154296875, timestamp=1662052900.1463711) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 9.04/11.81 result: MeasureResult(costs=(0.0296913874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6199190616607666, timestamp=1662052900.7870317) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.48/11.81 result: MeasureResult(costs=(0.181191088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0061700344085693, timestamp=1662052903.9128928) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.62/11.81 result: MeasureResult(costs=(0.1025708474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7484710216522217, timestamp=1662052905.7198098) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index c77b04602..225daf0ec 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 496.1427404700089, 'median': 496.0948851000012, 'std': 0.6810259431842657}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.6193124900001, 'median': 493.7237737500027, 'std': 0.820370130637166}
</pre></div>
</div>
</div>
@@ -706,178 +706,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.51/ 17.51 GFLOPS | Progress: (4/20) | 6.43 s
-[Task 1/25] Current/Best: 6.16/ 17.51 GFLOPS | Progress: (8/20) | 9.49 s
-[Task 1/25] Current/Best: 11.53/ 22.78 GFLOPS | Progress: (12/20) | 11.98 s
-[Task 1/25] Current/Best: 16.41/ 22.78 GFLOPS | Progress: (16/20) | 13.69 s
-[Task 1/25] Current/Best: 11.54/ 23.80 GFLOPS | Progress: (20/20) | 15.46 s Done.
+[Task 1/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (4/20) | 5.83 s
+[Task 1/25] Current/Best: 6.16/ 17.60 GFLOPS | Progress: (8/20) | 9.25 s
+[Task 1/25] Current/Best: 11.53/ 22.84 GFLOPS | Progress: (12/20) | 11.73 s
+[Task 1/25] Current/Best: 16.56/ 22.84 GFLOPS | Progress: (16/20) | 13.42 s
+[Task 1/25] Current/Best: 11.61/ 23.84 GFLOPS | Progress: (20/20) | 15.17 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.20/ 13.18 GFLOPS | Progress: (4/20) | 3.94 s
-[Task 2/25] Current/Best: 14.02/ 18.15 GFLOPS | Progress: (8/20) | 5.26 s
-[Task 2/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (12/20) | 6.63 s
-[Task 2/25] Current/Best: 12.33/ 20.72 GFLOPS | Progress: (16/20) | 7.90 s
-[Task 2/25] Current/Best: 20.37/ 20.72 GFLOPS | Progress: (20/20) | 9.52 s Done.
+[Task 2/25] Current/Best: 12.25/ 12.85 GFLOPS | Progress: (4/20) | 3.74 s
+[Task 2/25] Current/Best: 14.17/ 18.39 GFLOPS | Progress: (8/20) | 5.03 s
+[Task 2/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (12/20) | 6.36 s
+[Task 2/25] Current/Best: 12.24/ 20.59 GFLOPS | Progress: (16/20) | 7.61 s
+[Task 2/25] Current/Best: 19.35/ 20.59 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: 1.63/ 10.79 GFLOPS | Progress: (4/20) | 5.92 s
-[Task 3/25] Current/Best: 15.26/ 16.73 GFLOPS | Progress: (8/20) | 7.86 s
-[Task 3/25] Current/Best: 14.91/ 16.73 GFLOPS | Progress: (12/20) | 9.61 s
-[Task 3/25] Current/Best: 7.21/ 23.64 GFLOPS | Progress: (16/20) | 11.54 s
-[Task 3/25] Current/Best: 12.56/ 23.64 GFLOPS | Progress: (20/20) | 16.13 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.84 GFLOPS | Progress: (4/20) | 5.86 s
+[Task 3/25] Current/Best: 15.02/ 16.82 GFLOPS | Progress: (8/20) | 7.81 s
+[Task 3/25] Current/Best: 14.99/ 16.82 GFLOPS | Progress: (12/20) | 9.52 s
+[Task 3/25] Current/Best: 7.23/ 23.76 GFLOPS | Progress: (16/20) | 11.43 s
+[Task 3/25] Current/Best: 12.06/ 23.76 GFLOPS | Progress: (20/20) | 15.98 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.46/ 19.49 GFLOPS | Progress: (4/20) | 2.48 s
-[Task 4/25] Current/Best: 6.80/ 19.49 GFLOPS | Progress: (8/20) | 7.24 s
-[Task 4/25] Current/Best: 21.97/ 21.97 GFLOPS | Progress: (12/20) | 12.27 s
-[Task 4/25] Current/Best: 17.49/ 21.97 GFLOPS | Progress: (16/20) | 14.67 s
-[Task 4/25] Current/Best: 13.34/ 21.97 GFLOPS | Progress: (20/20) | 16.79 s Done.
+[Task 4/25] Current/Best: 9.56/ 20.35 GFLOPS | Progress: (4/20) | 2.41 s
+[Task 4/25] Current/Best: 6.78/ 20.35 GFLOPS | Progress: (8/20) | 7.08 s
+[Task 4/25] Current/Best: 22.42/ 22.42 GFLOPS | Progress: (12/20) | 12.02 s
+[Task 4/25] Current/Best: 16.21/ 22.42 GFLOPS | Progress: (16/20) | 14.41 s
+[Task 4/25] Current/Best: 13.25/ 22.42 GFLOPS | Progress: (20/20) | 16.52 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.55/ 10.25 GFLOPS | Progress: (4/20) | 2.65 s
-[Task 5/25] Current/Best: 11.69/ 11.83 GFLOPS | Progress: (8/20) | 4.72 s
-[Task 5/25] Current/Best: 10.64/ 17.92 GFLOPS | Progress: (12/20) | 7.91 s
-[Task 5/25] Current/Best: 10.88/ 22.52 GFLOPS | Progress: (16/20) | 9.35 s
-[Task 5/25] Current/Best: 12.03/ 22.52 GFLOPS | Progress: (20/20) | 11.28 s Done.
+[Task 5/25] Current/Best: 9.57/ 10.31 GFLOPS | Progress: (4/20) | 2.64 s
+[Task 5/25] Current/Best: 11.76/ 12.70 GFLOPS | Progress: (8/20) | 4.73 s
+[Task 5/25] Current/Best: 11.50/ 18.05 GFLOPS | Progress: (12/20) | 7.78 s
+[Task 5/25] Current/Best: 11.68/ 22.56 GFLOPS | Progress: (16/20) | 9.24 s
+[Task 5/25] Current/Best: 12.11/ 22.56 GFLOPS | Progress: (20/20) | 11.13 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.11/ 20.09 GFLOPS | Progress: (4/20) | 4.15 s
-[Task 6/25] Current/Best: 18.79/ 20.09 GFLOPS | Progress: (8/20) | 5.94 s
-[Task 6/25] Current/Best: 13.22/ 20.09 GFLOPS | Progress: (12/20) | 7.91 s
-[Task 6/25] Current/Best: 20.03/ 20.09 GFLOPS | Progress: (16/20) | 10.16 s
-[Task 6/25] Current/Best: 3.73/ 20.09 GFLOPS | Progress: (20/20) | 12.71 s Done.
+[Task 6/25] Current/Best: 12.01/ 20.11 GFLOPS | Progress: (4/20) | 4.12 s
+[Task 6/25] Current/Best: 18.87/ 20.11 GFLOPS | Progress: (8/20) | 5.92 s
+[Task 6/25] Current/Best: 13.34/ 20.11 GFLOPS | Progress: (12/20) | 7.88 s
+[Task 6/25] Current/Best: 20.00/ 20.11 GFLOPS | Progress: (16/20) | 10.15 s
+[Task 6/25] Current/Best: 3.73/ 20.11 GFLOPS | Progress: (20/20) | 12.66 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 10.75/ 12.88 GFLOPS | Progress: (4/20) | 3.70 s
-[Task 7/25] Current/Best: 19.95/ 21.19 GFLOPS | Progress: (8/20) | 5.25 s
-[Task 7/25] Current/Best: 15.96/ 21.19 GFLOPS | Progress: (12/20) | 7.18 s
-[Task 7/25] Current/Best: 12.18/ 21.19 GFLOPS | Progress: (16/20) | 9.23 s
-[Task 7/25] Current/Best: 6.37/ 21.74 GFLOPS | Progress: (20/20) | 11.70 s Done.
+[Task 7/25] Current/Best: 9.92/ 12.44 GFLOPS | Progress: (4/20) | 3.65 s
+[Task 7/25] Current/Best: 20.00/ 21.18 GFLOPS | Progress: (8/20) | 5.17 s
+[Task 7/25] Current/Best: 16.13/ 21.18 GFLOPS | Progress: (12/20) | 7.06 s
+[Task 7/25] Current/Best: 12.21/ 21.18 GFLOPS | Progress: (16/20) | 9.10 s
+[Task 7/25] Current/Best: 6.37/ 21.85 GFLOPS | Progress: (20/20) | 11.56 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.08/ 14.16 GFLOPS | Progress: (4/20) | 2.95 s
-[Task 8/25] Current/Best: 9.16/ 14.16 GFLOPS | Progress: (8/20) | 8.12 s
-[Task 8/25] Current/Best: 13.16/ 14.16 GFLOPS | Progress: (12/20) | 14.69 s
-[Task 8/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (16/20) | 16.81 s
-[Task 8/25] Current/Best: 19.73/ 19.73 GFLOPS | Progress: (20/20) | 23.89 s Done.
+[Task 8/25] Current/Best: 9.70/ 13.81 GFLOPS | Progress: (4/20) | 2.92 s
+[Task 8/25] Current/Best: 9.35/ 13.81 GFLOPS | Progress: (8/20) | 8.03 s
+[Task 8/25] Current/Best: 13.06/ 13.81 GFLOPS | Progress: (12/20) | 14.52 s
+[Task 8/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (16/20) | 16.65 s
+[Task 8/25] Current/Best: 19.30/ 19.30 GFLOPS | Progress: (20/20) | 23.64 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.29/ 15.56 GFLOPS | Progress: (4/20) | 11.97 s
-[Task 9/25] Current/Best: 23.27/ 23.27 GFLOPS | Progress: (8/20) | 13.75 s
-[Task 9/25] Current/Best: 8.22/ 23.27 GFLOPS | Progress: (12/20) | 16.28 s
-[Task 9/25] Current/Best: 17.77/ 23.27 GFLOPS | Progress: (16/20) | 19.14 s
-[Task 9/25] Current/Best: 8.96/ 23.27 GFLOPS | Progress: (20/20) | 27.75 s
+[Task 9/25] Current/Best: 14.37/ 15.79 GFLOPS | Progress: (4/20) | 11.99 s
+[Task 9/25] Current/Best: 23.45/ 23.45 GFLOPS | Progress: (8/20) | 13.77 s
+[Task 9/25] Current/Best: 8.30/ 23.45 GFLOPS | Progress: (12/20) | 16.29 s
+[Task 9/25] Current/Best: 17.90/ 23.45 GFLOPS | Progress: (16/20) | 19.12 s
+[Task 9/25] Current/Best: 9.21/ 23.45 GFLOPS | Progress: (20/20) | 27.55 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.34/ 18.34 GFLOPS | Progress: (4/20) | 2.63 s
-[Task 10/25] Current/Best: 15.60/ 18.34 GFLOPS | Progress: (8/20) | 4.30 s
-[Task 10/25] Current/Best: 12.83/ 18.87 GFLOPS | Progress: (12/20) | 5.86 s
-[Task 10/25] Current/Best: 19.08/ 20.23 GFLOPS | Progress: (16/20) | 6.98 s
-[Task 10/25] Current/Best: 8.76/ 20.23 GFLOPS | Progress: (20/20) | 8.52 s Done.
+[Task 10/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (4/20) | 2.60 s
+[Task 10/25] Current/Best: 15.63/ 18.13 GFLOPS | Progress: (8/20) | 4.24 s
+[Task 10/25] Current/Best: 12.64/ 18.89 GFLOPS | Progress: (12/20) | 5.79 s
+[Task 10/25] Current/Best: 19.19/ 20.40 GFLOPS | Progress: (16/20) | 6.91 s
+[Task 10/25] Current/Best: 8.82/ 20.40 GFLOPS | Progress: (20/20) | 8.44 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.29/ 18.11 GFLOPS | Progress: (4/20) | 3.43 s
-[Task 11/25] Current/Best: 16.86/ 18.11 GFLOPS | Progress: (8/20) | 6.28 s
-[Task 11/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (12/20) | 8.33 s
-[Task 11/25] Current/Best: 13.44/ 20.96 GFLOPS | Progress: (16/20) | 11.21 s
-[Task 11/25] Current/Best: 19.41/ 21.64 GFLOPS | Progress: (20/20) | 13.32 s Done.
+[Task 11/25] Current/Best: 12.29/ 18.20 GFLOPS | Progress: (4/20) | 3.40 s
+[Task 11/25] Current/Best: 16.64/ 18.20 GFLOPS | Progress: (8/20) | 6.19 s
+[Task 11/25] Current/Best: 16.21/ 18.20 GFLOPS | Progress: (12/20) | 8.31 s
+[Task 11/25] Current/Best: 13.44/ 21.01 GFLOPS | Progress: (16/20) | 11.24 s
+[Task 11/25] Current/Best: 19.46/ 21.53 GFLOPS | Progress: (20/20) | 13.34 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/ 18.00 GFLOPS | Progress: (4/20) | 5.80 s
-[Task 12/25] Current/Best: 5.16/ 18.00 GFLOPS | Progress: (8/20) | 9.78 s
-[Task 12/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (12/20) | 11.80 s
-[Task 12/25] Current/Best: 15.07/ 19.13 GFLOPS | Progress: (16/20) | 14.73 s
-[Task 12/25] Current/Best: 15.15/ 19.13 GFLOPS | Progress: (20/20) | 16.65 s Done.
+[Task 12/25] Current/Best: 7.81/ 17.99 GFLOPS | Progress: (4/20) | 5.71 s
+[Task 12/25] Current/Best: 5.19/ 17.99 GFLOPS | Progress: (8/20) | 9.61 s
+[Task 12/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (12/20) | 11.65 s
+[Task 12/25] Current/Best: 15.32/ 18.91 GFLOPS | Progress: (16/20) | 14.56 s
+[Task 12/25] Current/Best: 15.14/ 18.91 GFLOPS | Progress: (20/20) | 16.50 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.74/ 17.10 GFLOPS | Progress: (4/20) | 3.85 s
-[Task 13/25] Current/Best: 15.85/ 20.80 GFLOPS | Progress: (8/20) | 6.44 s
-[Task 13/25] Current/Best: 19.54/ 21.80 GFLOPS | Progress: (12/20) | 9.55 s
-[Task 13/25] Current/Best: 12.22/ 21.80 GFLOPS | Progress: (16/20) | 13.04 s
-[Task 13/25] Current/Best: 18.80/ 21.80 GFLOPS | Progress: (20/20) | 15.36 s Done.
+[Task 13/25] Current/Best: 8.69/ 17.31 GFLOPS | Progress: (4/20) | 3.77 s
+[Task 13/25] Current/Best: 15.72/ 20.90 GFLOPS | Progress: (8/20) | 6.35 s
+[Task 13/25] Current/Best: 19.52/ 21.97 GFLOPS | Progress: (12/20) | 9.39 s
+[Task 13/25] Current/Best: 12.30/ 21.97 GFLOPS | Progress: (16/20) | 12.87 s
+[Task 13/25] Current/Best: 18.51/ 21.97 GFLOPS | Progress: (20/20) | 15.19 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.78/ 13.78 GFLOPS | Progress: (4/20) | 3.46 s
-[Task 14/25] Current/Best: 6.08/ 13.78 GFLOPS | Progress: (8/20) | 5.63 s
-[Task 14/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (12/20) | 8.33 s
-[Task 14/25] Current/Best: 17.05/ 20.06 GFLOPS | Progress: (16/20) | 10.00 s Done.
+[Task 14/25] Current/Best: 13.32/ 13.32 GFLOPS | Progress: (4/20) | 3.47 s
+[Task 14/25] Current/Best: 6.11/ 13.32 GFLOPS | Progress: (8/20) | 5.64 s
+[Task 14/25] Current/Best: 20.15/ 20.15 GFLOPS | Progress: (12/20) | 8.31 s
+[Task 14/25] Current/Best: 17.02/ 20.15 GFLOPS | Progress: (16/20) | 9.95 s Done.
-[Task 14/25] Current/Best: 17.23/ 20.06 GFLOPS | Progress: (20/20) | 11.76 s
+[Task 14/25] Current/Best: 17.32/ 20.15 GFLOPS | Progress: (20/20) | 11.70 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.15/ 17.64 GFLOPS | Progress: (4/20) | 2.82 s
-[Task 15/25] Current/Best: 14.19/ 17.83 GFLOPS | Progress: (8/20) | 4.13 s
-[Task 15/25] Current/Best: 10.39/ 22.35 GFLOPS | Progress: (12/20) | 6.37 s
-[Task 15/25] Current/Best: 20.34/ 22.35 GFLOPS | Progress: (16/20) | 9.99 s
-[Task 15/25] Current/Best: 9.69/ 22.35 GFLOPS | Progress: (20/20) | 11.02 s
+[Task 15/25] Current/Best: 16.09/ 16.09 GFLOPS | Progress: (4/20) | 2.77 s
+[Task 15/25] Current/Best: 12.68/ 17.97 GFLOPS | Progress: (8/20) | 4.08 s
+[Task 15/25] Current/Best: 10.38/ 22.28 GFLOPS | Progress: (12/20) | 6.31 s
+[Task 15/25] Current/Best: 20.32/ 22.28 GFLOPS | Progress: (16/20) | 9.48 s
+[Task 15/25] Current/Best: 9.69/ 22.28 GFLOPS | Progress: (20/20) | 10.50 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (4/20) | 3.17 s
-[Task 16/25] Current/Best: 3.04/ 20.61 GFLOPS | Progress: (8/20) | 4.78 s
-[Task 16/25] Current/Best: 19.29/ 20.61 GFLOPS | Progress: (12/20) | 5.99 s
-[Task 16/25] Current/Best: 17.69/ 20.61 GFLOPS | Progress: (16/20) | 7.38 s
-[Task 16/25] Current/Best: 10.01/ 21.47 GFLOPS | Progress: (20/20) | 9.54 s Done.
+[Task 16/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (4/20) | 3.01 s
+[Task 16/25] Current/Best: 3.03/ 20.58 GFLOPS | Progress: (8/20) | 4.62 s
+[Task 16/25] Current/Best: 19.16/ 20.58 GFLOPS | Progress: (12/20) | 5.84 s
+[Task 16/25] Current/Best: 18.06/ 20.58 GFLOPS | Progress: (16/20) | 7.23 s
+[Task 16/25] Current/Best: 9.97/ 22.35 GFLOPS | Progress: (20/20) | 9.39 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.20/ 18.36 GFLOPS | Progress: (4/20) | 4.88 s
-[Task 17/25] Current/Best: 14.45/ 23.41 GFLOPS | Progress: (8/20) | 7.75 s
-[Task 17/25] Current/Best: 17.87/ 23.41 GFLOPS | Progress: (12/20) | 9.82 s
-[Task 17/25] Current/Best: 16.48/ 23.41 GFLOPS | Progress: (16/20) | 12.05 s
-[Task 17/25] Current/Best: 10.03/ 23.41 GFLOPS | Progress: (20/20) | 14.21 s Done.
+[Task 17/25] Current/Best: 13.50/ 18.37 GFLOPS | Progress: (4/20) | 4.80 s
+[Task 17/25] Current/Best: 14.23/ 23.34 GFLOPS | Progress: (8/20) | 7.69 s
+[Task 17/25] Current/Best: 16.80/ 23.34 GFLOPS | Progress: (12/20) | 9.77 s
+[Task 17/25] Current/Best: 16.47/ 23.34 GFLOPS | Progress: (16/20) | 12.02 s
+[Task 17/25] Current/Best: 10.02/ 23.34 GFLOPS | Progress: (20/20) | 14.20 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.55/ 18.07 GFLOPS | Progress: (4/20) | 3.82 s
-[Task 18/25] Current/Best: 10.61/ 19.62 GFLOPS | Progress: (8/20) | 7.50 s
-[Task 18/25] Current/Best: 18.99/ 19.62 GFLOPS | Progress: (12/20) | 9.45 s
-[Task 18/25] Current/Best: 10.00/ 19.62 GFLOPS | Progress: (16/20) | 13.28 s
-[Task 18/25] Current/Best: 20.51/ 20.51 GFLOPS | Progress: (20/20) | 14.80 s Done.
+[Task 18/25] Current/Best: 11.44/ 16.71 GFLOPS | Progress: (4/20) | 3.87 s
+[Task 18/25] Current/Best: 10.56/ 18.84 GFLOPS | Progress: (8/20) | 7.54 s
+[Task 18/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 9.47 s
+[Task 18/25] Current/Best: 9.97/ 19.28 GFLOPS | Progress: (16/20) | 13.37 s
+[Task 18/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (20/20) | 14.88 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.14/ 20.08 GFLOPS | Progress: (4/20) | 6.20 s
-[Task 19/25] Current/Best: 2.69/ 20.08 GFLOPS | Progress: (8/20) | 9.51 s
-[Task 19/25] Current/Best: 19.54/ 21.22 GFLOPS | Progress: (12/20) | 12.49 s
-[Task 19/25] Current/Best: 15.51/ 21.22 GFLOPS | Progress: (16/20) | 15.45 s
-[Task 19/25] Current/Best: 2.70/ 22.99 GFLOPS | Progress: (20/20) | 18.25 s Done.
+[Task 19/25] Current/Best: 7.10/ 20.13 GFLOPS | Progress: (4/20) | 6.19 s
+[Task 19/25] Current/Best: 2.69/ 20.13 GFLOPS | Progress: (8/20) | 9.52 s
+[Task 19/25] Current/Best: 19.68/ 21.48 GFLOPS | Progress: (12/20) | 12.45 s
+[Task 19/25] Current/Best: 15.49/ 22.58 GFLOPS | Progress: (16/20) | 15.51 s
+[Task 19/25] Current/Best: 2.70/ 23.08 GFLOPS | Progress: (20/20) | 18.30 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.99/ 15.19 GFLOPS | Progress: (4/20) | 3.44 s Done.
+[Task 20/25] Current/Best: 8.75/ 15.20 GFLOPS | Progress: (4/20) | 3.40 s Done.
Done.
-[Task 20/25] Current/Best: 10.06/ 15.19 GFLOPS | Progress: (8/20) | 6.87 s
-[Task 20/25] Current/Best: 2.32/ 16.60 GFLOPS | Progress: (12/20) | 10.81 s
-[Task 20/25] Current/Best: 12.28/ 16.60 GFLOPS | Progress: (16/20) | 14.83 s
-[Task 20/25] Current/Best: 12.12/ 21.53 GFLOPS | Progress: (20/20) | 16.96 s
+[Task 20/25] Current/Best: 9.73/ 15.20 GFLOPS | Progress: (8/20) | 6.80 s
+[Task 20/25] Current/Best: 2.30/ 16.43 GFLOPS | Progress: (12/20) | 10.69 s
+[Task 20/25] Current/Best: 12.35/ 16.43 GFLOPS | Progress: (16/20) | 14.65 s
+[Task 20/25] Current/Best: 12.50/ 22.26 GFLOPS | Progress: (20/20) | 16.77 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.39/ 17.58 GFLOPS | Progress: (4/20) | 3.33 s
-[Task 21/25] Current/Best: 14.44/ 17.58 GFLOPS | Progress: (8/20) | 4.94 s
-[Task 21/25] Current/Best: 1.61/ 17.58 GFLOPS | Progress: (12/20) | 7.12 s
-[Task 21/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (16/20) | 10.69 s
-[Task 21/25] Current/Best: 4.47/ 18.07 GFLOPS | Progress: (20/20) | 18.07 s
+[Task 21/25] Current/Best: 6.41/ 17.71 GFLOPS | Progress: (4/20) | 3.30 s
+[Task 21/25] Current/Best: 14.68/ 17.71 GFLOPS | Progress: (8/20) | 4.89 s
+[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 7.00 s
+[Task 21/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (16/20) | 10.55 s
+[Task 21/25] Current/Best: 4.47/ 18.04 GFLOPS | Progress: (20/20) | 17.87 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) | 2.74 s
-[Task 22/25] Current/Best: 9.03/ 21.63 GFLOPS | Progress: (8/20) | 4.81 s
-[Task 22/25] Current/Best: 19.74/ 21.63 GFLOPS | Progress: (12/20) | 7.18 s
-[Task 22/25] Current/Best: 15.31/ 21.63 GFLOPS | Progress: (16/20) | 9.30 s
-[Task 22/25] Current/Best: 14.58/ 21.63 GFLOPS | Progress: (20/20) | 11.06 s Done.
+[Task 22/25] Current/Best: 2.70/ 17.02 GFLOPS | Progress: (4/20) | 2.70 s
+[Task 22/25] Current/Best: 8.68/ 22.01 GFLOPS | Progress: (8/20) | 4.75 s
+[Task 22/25] Current/Best: 19.98/ 22.01 GFLOPS | Progress: (12/20) | 7.14 s
+[Task 22/25] Current/Best: 15.61/ 22.01 GFLOPS | Progress: (16/20) | 9.31 s
+[Task 22/25] Current/Best: 14.05/ 22.01 GFLOPS | Progress: (20/20) | 10.99 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.43/ 20.17 GFLOPS | Progress: (4/20) | 3.29 s
-[Task 23/25] Current/Best: 15.71/ 20.17 GFLOPS | Progress: (8/20) | 6.75 s
-[Task 23/25] Current/Best: 20.88/ 21.31 GFLOPS | Progress: (12/20) | 8.63 s
-[Task 23/25] Current/Best: 6.11/ 21.31 GFLOPS | Progress: (16/20) | 15.88 s
-[Task 23/25] Current/Best: 7.64/ 21.31 GFLOPS | Progress: (20/20) | 20.18 s Done.
+[Task 23/25] Current/Best: 17.68/ 20.73 GFLOPS | Progress: (4/20) | 3.30 s
+[Task 23/25] Current/Best: 13.76/ 20.73 GFLOPS | Progress: (8/20) | 6.80 s
+[Task 23/25] Current/Best: 20.94/ 21.42 GFLOPS | Progress: (12/20) | 8.64 s
+[Task 23/25] Current/Best: 6.40/ 21.42 GFLOPS | Progress: (16/20) | 15.66 s
+[Task 23/25] Current/Best: 7.91/ 21.42 GFLOPS | Progress: (20/20) | 19.88 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.57/ 8.57 GFLOPS | Progress: (4/20) | 11.84 s
-[Task 24/25] Current/Best: 3.54/ 8.57 GFLOPS | Progress: (8/20) | 23.09 s
-[Task 24/25] Current/Best: 4.30/ 8.57 GFLOPS | Progress: (12/20) | 33.83 s Done.
+[Task 24/25] Current/Best: 8.47/ 8.47 GFLOPS | Progress: (4/20) | 11.82 s
+[Task 24/25] Current/Best: 2.15/ 8.47 GFLOPS | Progress: (8/20) | 22.86 s
+[Task 24/25] Current/Best: 4.27/ 8.47 GFLOPS | Progress: (12/20) | 34.41 s Done.
-[Task 24/25] Current/Best: 7.16/ 8.84 GFLOPS | Progress: (16/20) | 39.56 s
-[Task 24/25] Current/Best: 3.32/ 8.84 GFLOPS | Progress: (20/20) | 45.66 s Done.
+[Task 24/25] Current/Best: 6.20/ 8.57 GFLOPS | Progress: (16/20) | 40.09 s
+[Task 24/25] Current/Best: 3.37/ 8.82 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/ 2.93 GFLOPS | Progress: (4/20) | 11.65 s
-[Task 25/25] Current/Best: 5.63/ 7.74 GFLOPS | Progress: (8/20) | 23.00 s
-[Task 25/25] Current/Best: 5.69/ 7.74 GFLOPS | Progress: (12/20) | 34.32 s
-[Task 25/25] Current/Best: 5.75/ 8.59 GFLOPS | Progress: (16/20) | 36.11 s
-[Task 25/25] Current/Best: 2.90/ 8.79 GFLOPS | Progress: (20/20) | 46.83 s
+[Task 25/25] Current/Best: 1.55/ 2.94 GFLOPS | Progress: (4/20) | 11.63 s
+[Task 25/25] Current/Best: 5.90/ 7.84 GFLOPS | Progress: (8/20) | 22.90 s
+[Task 25/25] Current/Best: 6.01/ 7.84 GFLOPS | Progress: (12/20) | 34.39 s
+[Task 25/25] Current/Best: 5.85/ 8.49 GFLOPS | Progress: (16/20) | 36.11 s
+[Task 25/25] Current/Best: 2.89/ 8.81 GFLOPS | Progress: (20/20) | 46.81 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -943,8 +943,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621105
-class='n02123159 tiger cat' with probability=0.356377
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
+class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -981,8 +981,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 415.61734948000776, 'median': 415.4157348999888, 'std': 1.2347701512066156}
-unoptimized: {'mean': 496.1427404700089, 'median': 496.0948851000012, 'std': 0.6810259431842657}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 411.3008441899956, 'median': 410.90171700000155, 'std': 0.9522105819474678}
+unoptimized: {'mean': 493.6193124900001, 'median': 493.7237737500027, 'std': 0.820370130637166}
</pre></div>
</div>
</div>
@@ -996,7 +996,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 32.700 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 25.791 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 91d242098..a8427f772 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.213e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.286e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 3f2eb5aad..62170bd65 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x1b54f660)), stage(b, placeholder(b, 0x1b5709a0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x1b179bd0)), stage(b, placeholder(b, 0x1b21b050)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index d6d79da2b..0b6096794 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:36.209</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:22.702</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,39 +336,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:32.700</p></td>
+<td><p>10:25.791</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:05.533</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
+<td><p>01:00.946</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.941</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
+<td><p>00:57.459</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:31.409</p></td>
+<td><p>00:30.934</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:24.250</p></td>
+<td><p>00:25.904</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.700</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.816</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.520</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.700</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.146</p></td>
+<td><p>00:00.143</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.004</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
@@ -379,11 +379,11 @@
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 5cb8f2a04..63c977dde 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -542,8 +542,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
-naive: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+naive: 0.000006
</pre></div>
</div>
</div>
@@ -635,7 +635,7 @@ factor to be the number of threads on your CPU.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.000028
+vector: 0.000025
@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"),
@@ -668,10 +668,10 @@ vector: 0.000028
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 6.7660700005944815e-06 1.0
- naive 6.6816000000000005e-06 0.987515647844752
-parallel 6.9194e-06 1.0226616040614487
- vector 2.7578599999999997e-05 4.07601458417913
+ numpy 8.43765000354324e-06 1.0
+ naive 5.8182e-06 0.6895521854493551
+parallel 7.0312e-06 0.8333125926113757
+ vector 2.4595500000000002e-05 2.9149703993021236
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -987,7 +987,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018101
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1030,7 +1030,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 3.393141
+none: 3.417285
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1097,7 +1097,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.311018
+blocking: 0.305122
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1158,7 +1158,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.333327
+vectorization: 0.336167
@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], []),
@@ -1215,7 +1215,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.119382
+loop permutation: 0.116110
@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], []),
@@ -1293,7 +1293,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.110051
+array packing: 0.108080
@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], []),
@@ -1369,7 +1369,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.110626
+block caching: 0.110487
@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], []),
@@ -1438,7 +1438,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.146517
+parallelization: 0.145963
@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], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.3931412672 1.0
- blocking 0.311018449 0.09166091963410959
- vectorization 0.3333269217 0.09823549786215044
-loop permutation 0.11938214259999999 0.035183369391075615
- array packing 0.11005143619999999 0.032433496731721335
- block caching 0.1106260794 0.03260285107177043
- parallelization 0.1465170597 0.04318035948468041
+ none 3.4172851178999997 1.0
+ blocking 0.30512232399999994 0.08928793281009711
+ vectorization 0.33616703130000003 0.09837254419864808
+loop permutation 0.11610994780000002 0.033977249130254676
+ array packing 0.10808032809999998 0.03162754185592153
+ block caching 0.1104865881 0.03233168561828887
+ parallelization 0.1459627158 0.04271306337169122
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1538,7 +1538,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.941 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.946 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>