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 2022/09/29 18:58:16 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@3e3d900c66ba8caad6b491c60d1331be470f9cba)
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 eb99447a11 deploying docs (apache/tvm@3e3d900c66ba8caad6b491c60d1331be470f9cba)
eb99447a11 is described below
commit eb99447a113d1d2b5ea273652b6aa792e7658da4
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Sep 29 18:58:07 2022 +0000
deploying docs (apache/tvm@3e3d900c66ba8caad6b491c60d1331be470f9cba)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 302810 -> 330120 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22617 -> 23754 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1082 ++++++++++++++++----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 164 ++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 194 +---
.../work_with_microtvm/micro_autotune.rst.txt | 21 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 10 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 13 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 55 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../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_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 14 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 30 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 53 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
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 | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1082 ++++++++++++++++----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 164 ++-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 194 +---
docs/how_to/work_with_microtvm/micro_autotune.html | 17 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
.../doxygen/classtvm_1_1runtime_1_1ModuleNode.html | 2 +-
...vm_1_1runtime_1_1ModuleNode__inherit__graph.svg | 260 ++---
...1_1runtime_1_1vm_1_1VirtualMachine-members.html | 58 +-
...lasstvm_1_1runtime_1_1vm_1_1VirtualMachine.html | 329 +++++-
...untime_1_1vm_1_1VirtualMachine__coll__graph.svg | 384 +++----
...ime_1_1vm_1_1VirtualMachine__inherit__graph.svg | 200 ++--
docs/reference/api/doxygen/functions_func_i.html | 8 +-
docs/reference/api/doxygen/functions_func_p.html | 3 +
docs/reference/api/doxygen/functions_func_r.html | 4 +-
docs/reference/api/doxygen/functions_func_s.html | 14 +-
docs/reference/api/doxygen/functions_func_t.html | 4 +-
docs/reference/api/doxygen/functions_func_u.html | 2 +-
docs/reference/api/doxygen/functions_func_v.html | 4 +-
docs/reference/api/doxygen/functions_i.html | 12 +-
docs/reference/api/doxygen/functions_k.html | 4 +-
docs/reference/api/doxygen/functions_o.html | 16 +-
docs/reference/api/doxygen/functions_p.html | 8 +-
docs/reference/api/doxygen/functions_r.html | 2 +-
docs/reference/api/doxygen/functions_s.html | 21 +-
docs/reference/api/doxygen/functions_t.html | 6 +-
docs/reference/api/doxygen/functions_v.html | 10 +-
docs/reference/api/doxygen/functions_vars_o.html | 6 +
docs/reference/api/doxygen/functions_vars_p.html | 3 +
docs/reference/api/doxygen/functions_vars_s.html | 3 +
.../api/doxygen/runtime_2vm_2vm_8h_source.html | 27 +-
docs/reference/api/doxygen/search/all_10.js | 4 +-
docs/reference/api/doxygen/search/all_11.js | 6 +-
docs/reference/api/doxygen/search/all_13.js | 8 +-
docs/reference/api/doxygen/search/all_14.js | 15 +-
docs/reference/api/doxygen/search/all_15.js | 10 +-
docs/reference/api/doxygen/search/all_16.js | 2 +-
docs/reference/api/doxygen/search/all_17.js | 4 +-
docs/reference/api/doxygen/search/all_18.js | 2 +-
docs/reference/api/doxygen/search/all_a.js | 2 +-
docs/reference/api/doxygen/search/all_c.js | 2 +-
docs/reference/api/doxygen/search/all_e.js | 2 +-
docs/reference/api/doxygen/search/functions_10.js | 3 +-
docs/reference/api/doxygen/search/functions_12.js | 6 +-
docs/reference/api/doxygen/search/functions_13.js | 6 +-
docs/reference/api/doxygen/search/functions_14.js | 2 +-
docs/reference/api/doxygen/search/functions_15.js | 2 +-
docs/reference/api/doxygen/search/functions_16.js | 2 +-
docs/reference/api/doxygen/search/functions_9.js | 2 +-
docs/reference/api/doxygen/search/functions_d.js | 2 +-
docs/reference/api/doxygen/search/typedefs_f.js | 2 +-
docs/reference/api/doxygen/search/variables_11.js | 1 +
docs/reference/api/doxygen/search/variables_e.js | 4 +-
docs/reference/api/doxygen/search/variables_f.js | 1 +
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 8 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 265 +++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 30 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
173 files changed, 3735 insertions(+), 2253 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 1a78ef007a..749f250b96 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 8e911753f3..eb961b1b9c 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 65ce36eced..94ff721d14 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.817 seconds)
+ **Total running time of the script:** ( 1 minutes 11.226 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 85ffa6605e..ffeebdf485 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 934ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 967ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 19eb7c9c92..dcc4ba2fcb 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.zipa22a691e-31fc-4b6c-8680-46f0dbf2d894 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip685dce34-3af5-43ef-a312-c19e66a53b4b 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 fcc723a169..62f943125e 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 51.5MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 55.2MB/s]
47%|####7 | 19.7M/41.5M [00:00<00:00, 54.9MB/s]
60%|###### | 24.9M/41.5M [00:00<00:00, 46.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 45.3MB/s]
90%|########9 | 37.2M/41.5M [00:00<00:00, 43.2MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 47.1MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 41.2MB/s]
25%|##4 | 10.3M/41.5M [00:00<00:00, 33.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 33.8MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 46.6MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 51.5MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 46.3MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 44.9MB/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 2ab3ae0636..f903d30bca 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]
35%|###4 | 15.6M/44.7M [00:00<00:00, 163MB/s]
74%|#######3 | 32.9M/44.7M [00:00<00:00, 174MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 188MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
39%|###8 | 17.4M/44.7M [00:00<00:00, 182MB/s]
85%|########4 | 38.0M/44.7M [00:00<00:00, 202MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 206MB/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 7aebfc20cc..e860ce3988 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.976 seconds)
+ **Total running time of the script:** ( 1 minutes 14.438 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 ad0073258e..2597e7143f 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
=================
-**05:35.178** total execution time for **how_to_compile_models** files:
+**05:43.845** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:10.817 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:14.438 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:09.976 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.226 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.592 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.162 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:30.234 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.080 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:27.731 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.126 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.946 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.674 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.140 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.916 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.122 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.375 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.128 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.368 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.491 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.481 | 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 367ec3a3d7..b5a14f71da 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.8856 15.8379 16.1727 15.8223 0.1016
+ 16.1504 16.1103 16.4735 15.9836 0.1280
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 fc2c197acd..3ca9276c79 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%|2 | 3.94M/170M [00:00<00:04, 41.1MB/s]
6%|5 | 9.88M/170M [00:00<00:03, 53.4MB/s]
9%|8 | 15.0M/170M [00:00<00:03, 52.9MB/s]
12%|#1 | 20.0M/170M [00:00<00:03, 49.7MB/s]
15%|#4 | 24.8M/170M [00:00<00:03, 44.7MB/s]
17%|#7 | 29.1M/170M [00:00<00:03, 40.5MB/s]
20%|#9 | 33.8M/170M [00:00<00:03, 42.9MB/s]
23%|##2 | 38.8M/170M [00:00<00:03, 45.5MB/s]
26%|##6 | 44.2M/170M [00:00<00:02, 48.8MB/s]
29%|##8 | 48.9M/170M [00:01<00:02, 46.0MB/s]
31%|###1 | 53.4M/170M [00:01<00:02, 44.3MB/s]
34%|###3 | 57.7M/170M [00:01<00:02, 42.6MB/s]
36%|###6 | 61.8M/170M [00:01<00:02, 42.5MB/s]
39%|###8 | 65.9M/170M [00:01<00:02, 42.6MB/s]
42%|####1 | 70.8M/170M [00:01<00:02, 45.2MB/s]
44%|####4 | 75.2M/170M [00:01<00:02, 44.5MB/s]
47%|####6 | 79.5M/170M [00:01<00:02, 44.5MB/
s]
49%|####9 | 83.8M/170M [00:01<00:02, 42.0MB/s]
52%|#####1 | 87.8M/170M [00:02<00:02, 41.6MB/s]
55%|#####4 | 93.4M/170M [00:02<00:01, 46.4MB/s]
58%|#####7 | 97.9M/170M [00:02<00:01, 44.6MB/s]
60%|###### | 103M/170M [00:02<00:01, 46.3MB/s]
63%|######3 | 108M/170M [00:02<00:01, 47.8MB/s]
66%|######6 | 112M/170M [00:02<00:01, 48.4MB/s]
69%|######8 | 117M/170M [00:02<00:01, 40.6MB/s]
71%|#######1 | 121M/170M [00:02<00:01, 39.3MB/s]
75%|#######4 | 127M/170M [00:02<00:01, 44.0MB/s]
78%|#######7 | 132M/170M [00:03<00:00, 46.6MB/s]
81%|######## | 138M/170M [00:03<00:00, 50.2MB/s]
84%|########3 | 142M/170M [00:03<00:00, 45.3MB/s]
87%|########7 | 148M/170M [00:03<00:00, 49.6MB/s]
90%|######### | 153M/170M [00:03<00:00, 46.9MB/s]
93%|#########2| 158M/170M [00:03<00:00, 47.0MB/s]
96%|#########5| 162M/170M [00:03<00:00, 44.4MB/s]
99%|#########9| 168M/170M [00:03<00:00, 49.1MB/s]
100%|##########| 170M/170M [00:03<00:00, 45.5MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.36M/170M [00:00<00:03, 45.2MB/s]
6%|6 | 11.0M/170M [00:00<00:02, 59.4MB/s]
17%|#6 | 28.0M/170M [00:00<00:01, 114MB/s]
23%|##3 | 39.8M/170M [00:00<00:01, 117MB/s]
33%|###2 | 55.2M/170M [00:00<00:00, 133MB/s]
42%|####2 | 71.4M/170M [00:00<00:00, 145MB/s]
50%|##### | 85.2M/170M [00:00<00:00, 93.5MB/s]
57%|#####6 | 96.2M/170M [00:01<00:00, 81.0MB/s]
62%|######2 | 106M/170M [00:01<00:00, 82.3MB/s]
67%|######7 | 114M/170M [00:01<00:00, 67.1MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 66.5MB/s]
79%|#######9 | 135M/170M [00:01<00:00, 80.9MB/s]
88%|########8 | 150M/170M [00:01<00:00, 100MB/s]
96%|#########6| 163M/170M [00:01<00:00, 109MB/s]
100%|##########| 170M/170M [00:01<00:00, 96.5MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-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)
/venv/apache-tvm-py3.7/lib/python3.7/site-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 15.737 seconds)
+ **Total running time of the script:** ( 3 minutes 15.688 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 534536fb3f..1d8bcc6608 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]
31%|###1 | 4.24M/13.6M [00:00<00:00, 44.5MB/s]
65%|######4 | 8.76M/13.6M [00:00<00:00, 46.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 65.1MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 182MB/s]
@@ -414,7 +414,7 @@ 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)
- 90.4501 90.3762 94.1002 90.1241 0.4277
+ 90.5989 90.3383 106.4143 90.1573 1.6540
@@ -463,7 +463,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.573 seconds)
+ **Total running time of the script:** ( 1 minutes 20.100 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 62e7b10a8a..cc8aa0c346 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.4551 121.1747 126.9564 120.3551 1.0368
+ 120.9381 120.9379 122.1887 119.9629 0.3998
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 1.895 seconds)
+ **Total running time of the script:** ( 2 minutes 0.644 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 34258e74bc..61e1009d04 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 34.178 seconds)
+ **Total running time of the script:** ( 1 minutes 33.106 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 fbe5250a40..3f70d2f562 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3453/132723 [00:00<00:03, 34483.01KB/s]
8%|7 | 10043/132723 [00:00<00:02, 52949.32KB/s]
13%|#3 | 17680/132723 [00:00<00:01, 63637.40KB/s]
19%|#9 | 25395/132723 [00:00<00:01, 68966.26KB/s]
25%|##4 | 33016/132723 [00:00<00:01, 71575.53KB/s]
31%|### | 40746/132723 [00:00<00:01, 73518.37KB/s]
37%|###6 | 48455/132723 [00:00<00:01, 74681.30KB/s]
42%|####2 | 56197/132723 [00:00<00:01, 75550.84KB/s]
48%|####8 | 63906/132723 [00:00<00:00, 76025.18KB/s]
54%|#####3 | 71509/132723 [00:01<00:00, 75793.14KB/s]
60%|#####9 | 79089/132723 [00:01<00:00, 75628.58KB/s]
65%|######5 | 86653/132723 [00:01<00:00, 75352.89KB/s]
71%|####### | 94189/132723 [00:01<00:00, 75144.66KB/s]
77%|#######6 | 101810/132723 [00:01<00:00, 75453.21KB/s]
83%|########2 | 109509/132723 [00:01<00:00, 75911.56KB/s]
88%|########8
| 117271/132723 [00:01<00:00, 76420.57KB/s]
94%|#########4| 125094/132723 [00:01<00:00, 76961.06KB/s]
100%|##########| 132723/132723 [00:01<00:00, 73584.24KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4406/132723 [00:00<00:02, 44057.31KB/s]
10%|9 | 12776/132723 [00:00<00:01, 67372.59KB/s]
16%|#6 | 21346/132723 [00:00<00:01, 75737.75KB/s]
23%|##2 | 29917/132723 [00:00<00:01, 79671.89KB/s]
29%|##8 | 38446/132723 [00:00<00:01, 81695.28KB/s]
35%|###5 | 46933/132723 [00:00<00:01, 82770.23KB/s]
42%|####1 | 55537/132723 [00:00<00:00, 83837.84KB/s]
48%|####8 | 64108/132723 [00:00<00:00, 84430.69KB/s]
55%|#####4 | 72713/132723 [00:00<00:00, 84928.93KB/s]
61%|######1 | 81273/132723 [00:01<00:00, 85127.71KB/s]
68%|######7 | 89894/132723 [00:01<00:00, 85456.62KB/s]
74%|#######4 | 98516/132723 [00:01<00:00, 85687.10KB/s]
81%|######## | 107163/132723 [00:01<00:00, 85921.67KB/s]
87%|########7 | 115791/132723 [00:01<00:00, 86027.69KB/s]
94%|#########3| 124394/132723 [00:01<00:00, 85955.34KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83011.90KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 52.476 seconds)
+ **Total running time of the script:** ( 2 minutes 51.090 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 982625db87..f6c72d19ee 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:29.276** total execution time for **how_to_deploy_models** files:
+**12:26.900** 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``) | 03:15.737 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:15.688 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:52.476 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:51.090 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:01.895 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:00.644 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:34.178 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:33.106 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:19.573 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:20.100 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.473 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.154 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.223 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.209 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.713 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.902 | 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 4b4fed1503..fab3b55544 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb112a9ba-dd2d-45e2-b293-671dfb3805f6 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb93788b8-dfeb-4af6-aaba-3f2f10d0f519 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 19cc5cc5d9..bb009ae658 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
=================
-**00:45.251** total execution time for **how_to_extend_tvm** files:
+**00:45.193** 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``) | 00:41.806 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:41.855 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.338 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.017 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.993 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 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 95c4b84eba..33045387b1 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: 6915us [6915us] (45.65%; 45.65%)
- FoldScaleAxis: 8232us [7us] (54.35%; 54.35%)
- FoldConstant: 8225us [1724us] (54.30%; 99.91%)
- InferType: 6500us [6500us] (42.91%; 79.04%)
+ InferType: 6743us [6743us] (46.16%; 46.16%)
+ FoldScaleAxis: 7866us [5us] (53.84%; 53.84%)
+ FoldConstant: 7861us [1606us] (53.81%; 99.94%)
+ InferType: 6255us [6255us] (42.82%; 79.57%)
@@ -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: 6528us [6528us] (44.66%; 44.66%)
- FoldScaleAxis: 8089us [6us] (55.34%; 55.34%)
- FoldConstant: 8083us [1735us] (55.30%; 99.93%)
- InferType: 6348us [6348us] (43.43%; 78.53%)
+ InferType: 6279us [6279us] (44.43%; 44.43%)
+ FoldScaleAxis: 7853us [4us] (55.57%; 55.57%)
+ FoldConstant: 7848us [1606us] (55.54%; 99.94%)
+ InferType: 6242us [6242us] (44.17%; 79.54%)
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 67f51ce2a8..f77f9bb54d 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 50.151966 ms
+ Convolution: 35.024513 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 095ae29a56..3abe00f7a1 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: 13.346815 ms
+ conv2d with tensor core: 12.029952 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 e85235f043..fa7ab62d26 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: 0.018818
- Baseline: 3.422008
+ Numpy running time: 0.019078
+ Baseline: 3.463612
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.310735
+ Opt1: 0.309250
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.343904
+ Opt2: 0.342270
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116739
+ Opt3: 0.121195
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109420
+ Opt4: 0.109486
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111505
+ Opt5: 0.111077
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.148249
+ Opt6: 0.147532
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 5f5b52d301..40cd6dacea 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.229** total execution time for **how_to_optimize_operators** files:
+**00:35.323** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.615 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.757 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.430 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.417 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.183 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.150 | 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 a1379eb8f0..b04fc8d71a 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
=================
-**06:41.239** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:54.408** 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``) | 03:26.432 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:42.823 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:30.415 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:30.060 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:59.818 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:59.349 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:23.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:21.234 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.924 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.611 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:10.550 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:10.330 | 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 7ddf41b5b5..750e934e65 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
@@ -240,109 +240,483 @@ 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, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_2: int32 = (rc.outer.outer*72)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_2 < 328), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- }
- for (rc.outer.inner: int32, 0, 8) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 96)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 97)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 98)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 99)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 100)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 101)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 102)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 103)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 104)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 105)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 106)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 107)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 192)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 288)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 193)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 289)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 194)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 290)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 195)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 291)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 196)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 292)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 197)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 293)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 198)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 294)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 199)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 295)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 200)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 296)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 201)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 297)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 202)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 298)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 203)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 299)]))
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -397,7 +771,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.292 ms
+ Execution time of this operator: 0.356 ms
@@ -445,36 +819,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ 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=8)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_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=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
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=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_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_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
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)
@@ -494,14 +868,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
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=392)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -519,90 +893,430 @@ 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__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[2016];
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
__shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[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) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 56) {
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 40) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- if (((int)threadIdx.x) < 328) {
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 96)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 97)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 98)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 99)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 100)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 101)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 102)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 103)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 104)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 106)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 107)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 192)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 288)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 193)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 289)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 194)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 290)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 195)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 291)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 196)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 292)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 197)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 293)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 198)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 294)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 199)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 295)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 200)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 296)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 201)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 297)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 202)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 298)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 203)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 299)]));
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -664,7 +1378,7 @@ 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 26.432 seconds)
+ **Total running time of the script:** ( 3 minutes 42.823 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 8b52b36119..5fdac3d7bb 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2002 8.1987 8.2049 8.1970 0.0034
+ 8.1801 8.1762 8.1909 8.1731 0.0078
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 5fab73f8a4..6380c14b4b 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 751.4023 751.0141 752.3609 750.8318 0.6819
+ 750.4536 747.6420 756.7698 746.9488 4.4752
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 30.415 seconds)
+ **Total running time of the script:** ( 1 minutes 30.060 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 fbc5e819a5..641569b36a 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
@@ -397,104 +397,80 @@ 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], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [256], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
- {
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_4: int32 = (i.inner*16)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_5: int32 = ((i.inner*16) + 1)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_6: int32 = ((i.inner*16) + 2)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_7: int32 = ((i.inner*16) + 3)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_8: int32 = ((i.inner*16) + 4)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_9: int32 = ((i.inner*16) + 5)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_10: int32 = ((i.inner*16) + 6)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_11: int32 = ((i.inner*16) + 7)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_12: int32 = ((i.inner*16) + 8)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_13: int32 = ((i.inner*16) + 9)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_14: int32 = ((i.inner*16) + 10)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_15: int32 = ((i.inner*16) + 11)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_16: int32 = ((i.inner*16) + 12)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_17: int32 = ((i.inner*16) + 13)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_18: int32 = ((i.inner*16) + 14)
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_19: int32 = ((i.inner*16) + 15)
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*4096) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 128) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ }
}
}
}
@@ -550,7 +526,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.947 ms
+ Execution time of this operator: 1.721 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 ec07f74ac1..251f59718c 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:34.736** total execution time for **how_to_tune_with_autotvm** files:
+**00:30.749** 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``) | 00:34.699 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:30.710 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.023 | 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_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 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 14d555bbc9..e38a0cb43b 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
@@ -277,7 +277,8 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 35.55/35.55 result: MeasureResult(costs=(0.006511551764705883,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9945309162139893, timestamp=1664473011.6994371) [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5279801
+ No: 2 GFLOPS: 0.00/35.55 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
@@ -399,8 +400,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10036027
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5392612
+ No: 3 GFLOPS: 0.00/35.55 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
@@ -522,9 +523,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,449385
- No: 3 GFLOPS: 2.49/2.49 result: MeasureResult(costs=(0.0929771955,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.139984130859375, timestamp=1664462703.714772) [('tile_f', [-1, 16, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4076520
- No: 4 GFLOPS: 0.00/2.49 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8305955
+ No: 4 GFLOPS: 7.41/35.55 result: MeasureResult(costs=(0.03122363275,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.096970558166504, timestamp=1664473014.987342) [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2277513
+ No: 5 GFLOPS: 8.11/35.55 result: MeasureResult(costs=(0.02855320725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4308624267578125, timestamp=1664473017.5918832) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8098924
+ No: 6 GFLOPS: 0.00/35.55 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
@@ -646,8 +648,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7861778
- No: 5 GFLOPS: 0.00/2.49 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9320977
+ No: 7 GFLOPS: 0.00/35.55 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
@@ -769,8 +771,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10025787
- No: 6 GFLOPS: 0.00/2.49 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8195926
+ No: 8 GFLOPS: 0.00/35.55 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
@@ -892,8 +894,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6963541
- No: 7 GFLOPS: 0.00/2.49 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5484152
+ No: 9 GFLOPS: 0.00/35.55 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
@@ -1015,9 +1017,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3646517
- No: 8 GFLOPS: 83.95/83.95 result: MeasureResult(costs=(0.002757704589285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8263216018676758, timestamp=1664462708.1927118) [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1841668
- No: 9 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4868236
+ No: 10 GFLOPS: 0.00/35.55 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
@@ -1139,8 +1140,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7607118
- No: 10 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9837459
+ No: 11 GFLOPS: 50.45/50.45 result: MeasureResult(costs=(0.004589104045454546,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2390820980072021, timestamp=1664473020.2844932) [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5619283
+ No: 12 GFLOPS: 0.00/50.45 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
@@ -1262,8 +1264,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9825760
- No: 11 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,471114
+ No: 13 GFLOPS: 0.00/50.45 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
@@ -1385,8 +1387,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9264322
- No: 12 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4158613
+ No: 14 GFLOPS: 0.00/50.45 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
@@ -1508,8 +1510,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10155113
- No: 13 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6504711
+ No: 15 GFLOPS: 354.13/354.13 result: MeasureResult(costs=(0.0006537152418300654,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.526313304901123, timestamp=1664473022.0321066) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7067967
+ No: 16 GFLOPS: 0.00/354.13 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
@@ -1631,8 +1634,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3935020
- No: 14 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4314821
+ No: 17 GFLOPS: 0.00/354.13 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
@@ -1754,8 +1757,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4239545
- No: 15 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9077245
+ No: 18 GFLOPS: 0.00/354.13 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
@@ -1877,9 +1880,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2663478
- No: 16 GFLOPS: 88.06/88.06 result: MeasureResult(costs=(0.0026287926721311476,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3867878913879395, timestamp=1664462710.0466747) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1018709
- No: 17 GFLOPS: 0.00/88.06 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7688802
+ No: 19 GFLOPS: 68.68/354.13 result: MeasureResult(costs=(0.003370504290322581,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8591158390045166, timestamp=1664473024.0965714) [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9103762
+ No: 20 GFLOPS: 0.00/354.13 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
@@ -2001,132 +2004,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,329649
- No: 18 GFLOPS: 2.97/88.06 result: MeasureResult(costs=(0.07805895225000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.844818115234375, timestamp=1664462715.0883167) [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7952100
- No: 19 GFLOPS: 0.00/88.06 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4791464
- No: 20 GFLOPS: 332.34/332.34 result: MeasureResult(costs=(0.0006965726736111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3543648719787598, timestamp=1664462715.7876148) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3746622
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9975019
@@ -2181,9 +2059,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3746622
+ [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7067967
Finish loading 20 records
- Time cost of this operator: 0.001133
+ Time cost of this operator: 0.001007
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 4b3671f848..952705477e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -327,10 +327,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.4 98.721 (1, 2, 10, 10, 3) 2 1 [309.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.056 0.975 (1, 6, 10, 10) 1 1 [3.056]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.304 (1, 1, 10, 10, 3) 1 1 [0.954]
- Total_time - 313.41 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.5 98.724 (1, 2, 10, 10, 3) 2 1 [312.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.078 0.972 (1, 6, 10, 10) 1 1 [3.078]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.304 (1, 1, 10, 10, 3) 1 1 [0.962]
+ Total_time - 316.54 - - - - -
@@ -394,20 +394,15 @@ 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 134.4 97.999 (1, 6, 10, 10, 1) 2 1 [134.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.764 1.286 (1, 6, 10, 10) 1 1 [1.764]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.98 0.714 (1, 1, 10, 10, 3) 1 1 [0.98]
- Total_time - 137.144 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.8 97.468 (1, 6, 10, 10, 1) 2 1 [102.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.825 1.73 (1, 6, 10, 10) 1 1 [1.825]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.846 0.802 (1, 3, 10, 10, 1) 1 1 [0.846]
+ Total_time - 105.471 - - - - -
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 0.033 seconds)
-
-
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
.. only:: html
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 925e7444a1..4d2ab95b8d 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/tmpaovt4iji/images/random'
+ '/tmp/tmpe_uga4xj/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpaovt4iji/images/target contains 8144 images
- /tmp/tmpaovt4iji/images/random contains 5000 images
+ /tmp/tmpe_uga4xj/images/target contains 8144 images
+ /tmp/tmpe_uga4xj/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2246 - accuracy: 0.9222 - val_loss: 0.1557 - val_accuracy: 0.9452 - 47s/epoch - 143ms/step
+ 328/328 - 47s - loss: 0.2292 - accuracy: 0.9242 - val_loss: 0.1456 - val_accuracy: 0.9551 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0998 - accuracy: 0.9643 - val_loss: 0.1059 - val_accuracy: 0.9634 - 43s/epoch - 131ms/step
+ 328/328 - 44s - loss: 0.0946 - accuracy: 0.9665 - val_loss: 0.1179 - val_accuracy: 0.9607 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0675 - accuracy: 0.9751 - val_loss: 0.1475 - val_accuracy: 0.9502 - 43s/epoch - 131ms/step
+ 328/328 - 44s - loss: 0.0694 - accuracy: 0.9743 - val_loss: 0.0980 - val_accuracy: 0.9596 - 44s/epoch - 133ms/step
- <keras.callbacks.History object at 0x7f1cf88238d0>
+ <keras.callbacks.History object at 0x7f5ab1ae3ed0>
@@ -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 7.924 seconds)
+ **Total running time of the script:** ( 5 minutes 12.192 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 ac98738813..c5945b8bf2 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
=================
-**06:23.049** total execution time for **how_to_work_with_microtvm** files:
+**06:25.769** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:07.924 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:12.192 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:00.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:59.602 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.663 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.648 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.427 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.326 | 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 2a6dad126e..872a034926 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
=================
-**00:44.107** total execution time for **how_to_work_with_relay** files:
+**00:44.371** 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``) | 00:32.393 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.417 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.073 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.130 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.635 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.817 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 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 db672e4430..6f11f314f9 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 0x7f1c7f30b4d0>
+ <function my_cuda_math_rule at 0x7f5aaf717560>
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 1f23e216cd..771481b49e 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
=================
-**00:07.801** total execution time for **how_to_work_with_schedules** files:
+**00:07.910** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.473 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.540 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.017 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.044 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.577 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.578 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.541 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.551 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 13b969e731..6ea1262682 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/tmp4kdm3pk9/input0.cc'\nsource_filename = \"/tmp/tmp4kdm3pk9/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/tmp4de87wbl/input0.cc'\nsource_filename = \"/tmp/tmp4de87wbl/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 8a90e51a93..0fe575d275 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
=================
-**00:25.813** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:24.907** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.807 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:24.900 | 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 fd99b9823c..884a034d4b 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 27.22s!
+ resnet18_v1 inference graph built in 26.85s!
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 abb726edd9..10af4561eb 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 18.89s!
+ yolov3-tiny inference graph built in 18.56s!
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 30e91f0891..822e4ddfe2 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
=================
-**01:38.947** total execution time for **topic_vta_tutorials_frontend** files:
+**01:38.940** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.623 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.535 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.324 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.405 | 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 0cb5cb6457..8856678d21 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
=================
-**00:03.081** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.082** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.661 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.648 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.420 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.433 | 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 3423ebc7cd..efbe68eb00 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
=================
-**00:00.790** total execution time for **topic_vta_tutorials** files:
+**00:00.777** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.421 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.407 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.369 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.370 | 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 b7464ca2ad..ce163a2bd4 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
-
-
@@ -333,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.301 ms
+ Execution time of this operator: 93.233 ms
@@ -433,7 +426,7 @@ resume the status and do more 5 trials.
Resume search:
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-
+ .T
@@ -451,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.808 seconds)
+ **Total running time of the script:** ( 1 minutes 8.636 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 52c40a9ed8..2b57bef511 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: 3.91/3.91 result: MeasureResult(costs=(0.0687301974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.287923812866211, timestamp=1664461383.301415) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
- No: 2 GFLOPS: 12.63/12.63 result: MeasureResult(costs=(0.0212616538,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5117099285125732, timestamp=1664461383.8127928) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
- No: 3 GFLOPS: 2.88/12.63 result: MeasureResult(costs=(0.0931643488,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.641861915588379, timestamp=1664461386.475515) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
- No: 4 GFLOPS: 10.12/12.63 result: MeasureResult(costs=(0.0265207926,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6130192279815674, timestamp=1664461388.0758436) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
- No: 5 GFLOPS: 12.79/12.79 result: MeasureResult(costs=(0.0209909008,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5884706974029541, timestamp=1664461388.946107) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
- No: 6 GFLOPS: 9.70/12.79 result: MeasureResult(costs=(0.027673180000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5938694477081299, timestamp=1664461389.5622501) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
- No: 7 GFLOPS: 9.95/12.79 result: MeasureResult(costs=(0.0269672574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8651423454284668, timestamp=1664461391.1939929) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
- No: 8 GFLOPS: 10.48/12.79 result: MeasureResult(costs=(0.0256231464,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6375958919525146, timestamp=1664461391.7707944) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
- No: 9 GFLOPS: 10.89/12.79 result: MeasureResult(costs=(0.0246470778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5358297824859619, timestamp=1664461392.4573696) [('tile_y', [-1, 2]), ('tile_x', [-1, 32])],None,51
- No: 10 GFLOPS: 10.55/12.79 result: MeasureResult(costs=(0.025443792799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6330265998840332, timestamp=1664461393.077525) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+ No: 1 GFLOPS: 9.92/9.92 result: MeasureResult(costs=(0.027060563000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6474769115447998, timestamp=1664471686.3018281) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
+ No: 2 GFLOPS: 2.35/9.92 result: MeasureResult(costs=(0.114190905,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.023916482925415, timestamp=1664471688.3390615) [('tile_y', [-1, 8]), ('tile_x', [-1, 2])],None,13
+ No: 3 GFLOPS: 13.34/13.34 result: MeasureResult(costs=(0.020119287399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5565180778503418, timestamp=1664471689.8299425) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+ No: 4 GFLOPS: 11.49/13.34 result: MeasureResult(costs=(0.023359496799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5389089584350586, timestamp=1664471691.3733964) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+ No: 5 GFLOPS: 2.55/13.34 result: MeasureResult(costs=(0.1052811178,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8254051208496094, timestamp=1664471693.3320937) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 6 GFLOPS: 11.49/13.34 result: MeasureResult(costs=(0.0233591384,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5382630825042725, timestamp=1664471693.8775823) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
+ No: 7 GFLOPS: 10.41/13.34 result: MeasureResult(costs=(0.0257923654,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5645241737365723, timestamp=1664471695.451878) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+ No: 8 GFLOPS: 11.38/13.34 result: MeasureResult(costs=(0.0235804342,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5666143894195557, timestamp=1664471696.0424912) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+ No: 9 GFLOPS: 8.55/13.34 result: MeasureResult(costs=(0.0313859866,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6206293106079102, timestamp=1664471696.782382) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+ No: 10 GFLOPS: 0.95/13.34 result: MeasureResult(costs=(0.28130801499999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.62048864364624, timestamp=1664471701.4472315) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 8ccd893387..377e67c58b 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 510.9940208499984, 'median': 510.723029199994, 'std': 1.8448765714679003}
+ {'mean': 517.7567010299754, 'median': 517.5474089998715, 'std': 2.42827195278956}
@@ -554,30 +554,29 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 16.39/ 17.73 GFLOPS | Progress: (4/20) | 10.03 s
[Task 1/25] Current/Best: 7.48/ 19.09 GFLOPS | Progress: (8/20) | 13.89 s
[Task 1/25] Current/Best: 10.67/ 19.09 GFLOPS | Progress: (12/20) | 16.47 s
[Task 1/25] Current/Best: 9.00/ 19.09 GFLOPS | Progress: (16/20) | 19.76 s
[Task 1/25] Current/Best: 8.62/ 23.07 GFLOPS | Progress: (20/20) | 23.44 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 15.09/ 15.09 GFLOPS | Progress: (4/20) | 3.65 s
[Task 2/25] Current/Best: 3.52/ 20.31 GFLOPS | Progress: (8/20) | 4.71 s
[Task 2/25] Current/Best: 15.39/ 20.31 GFLOPS | Progress: (12/20) | 6.05 s
[Task 2/25] Current/Best: 10.56/ 20.31 GFLOPS | Progress: (16/20) | 9.34 s
[Task 2/25] Current/Best: 19.65/ 20.31 GFLOPS | Progress: (20/20) | 10.34 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 19.56/ 19.56 GFLOPS | Progress: (4/20) | 5.07 s
[Task 3/25] Current/Best: 13.69/ 19.56 GFLOPS | Progress: (8/20) | 7.36 s
[Task 3/25] Current/Best: 23.65/ 23.65 GFLOPS | Progress: (12/20) | 9.14 s
[Task 3/25] Current/Best: 14.44/ 23.65 GFLOPS | Progress: (16/20) | 11.66 s
[Task 3/25] Current/Best: 13.92/ 23.65 GFLOPS | Progress: (20/20) | 13.67 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.90/ 17.32 GFLOPS | Progress: (4/20) | 7.08 s
[Task 4/25] Current/Best: 15.85/ 18.25 GFLOPS | Progress: (8/20) | 8.64 s
[Task 4/25] Current/Best: 6.51/ 18.25 GFLOPS | Progress: (12/20) | 10.45 s
[Task 4/25] Current/Best: 14.81/ 18.25 GFLOPS | Progress: (16/20) | 12.60 s
[Task 4/25] Current/Best: 11.28/ 20.96 GFLOPS | Progress: (20/20) | 15.29 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 14.27/ 16.14 GFLOPS | Progress: (4/20) | 3.67 s
[Task 5/25] Current/Best: 13.13/ 17.15 GFLOPS | Progress: (8/20) | 5.37 s
[Task 5/25] Current/Best: 20.95/ 20.95 GFLOPS | Progress: (12/20) | 7.33 s
[Task 5/25] Current/Best: 4.03/ 20.95 GFLOPS | Progress: (16/20) | 9.69 s
[Task 5/25] Current/Best: 13.03/ 22.60 GFLOPS | Progress: (20/20) | 11.61 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 20.30/ 21.96 GFLOPS | Progress: (4/20) | 3.97 s
[Task 6/25] Current/Best: 17.82/ 21.96 GFLOPS | Progress: (8/20) | 6.68 s
[Task 6/25] Current/Best: 9.22/ 21.96 GFLOPS | Progress: (12/20) | 8.85 s
[Task 6/25] Current/Best: 10.08/ 21.96 GFLOPS | Progress: (16/20) | 13.35 s
[Task 6/25] Current/Best: 17.03/ 21.96 GFLOPS | Progress: (20/20) | 15.91 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 4.42/ 15.28 GFLOPS | Progress: (4/20) | 4.30 s
[Task 7/25] Current/Best: 17.63/ 17.63 GFLOPS | Progress: (8/20) | 7.38 s
[Task 7/25] Current/Best: 9.45/ 21.08 GFLOPS | Progress: (12/20) | 9.11 s
[Task 7/25] Current/Best: 12.01/ 21.08 GFLOPS | Progress: (16/20) | 11.29 s
[Task 7/25] Current/Best: 6.06/ 21.08 GFLOPS | Progress: (20/20) | 13.54 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.73/ 15.10 GFLOPS | Progress: (4/20) | 4.44 s
[Task 8/25] Current/Best: 1.35/ 15.10 GFLOPS | Progress: (8/20) | 8.75 s
[Task 8/25] Current/Best: 14.88/ 15.10 GFLOPS | Progress: (12/20) | 10.70 s
[Task 8/25] Current/Best: 15.82/ 15.82 GFLOPS | Progress: (16/20) | 12.79 s
[Task 8/25] Current/Best: 10.08/ 22.85 GFLOPS | Progress: (20/20) | 19.53 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.29/ 21.41 GFLOPS | Progress: (4/20) | 8.56 s
[Task 9/25] Current/Best: 12.69/ 21.41 GFLOPS | Progress: (8/20) | 10.32 s
[Task 9/25] Current/Best: 15.08/ 23.20 GFLOPS | Progress: (12/20) | 11.62 s
[Task 9/25] Current/Best: 9.92/ 23.20 GFLOPS | Progress: (16/20) | 14.49 s
[Task 9/25] Current/Best: 12.57/ 23.20 GFLOPS | Progress: (20/20) | 18.55 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 15.09/ 17.63 GFLOPS | Progress: (4/20) | 3.50 s
[Task 10/25] Current/Best: 13.04/ 17.63 GFLOPS | Progress: (8/20) | 5.19 s
[Task 10/25] Current/Best: 16.78/ 18.63 GFLOPS | Progress: (12/20) | 6.46 s
[Task 10/25] Current/Best: 10.99/ 18.63 GFLOPS | Progress: (16/20) | 8.03 s
[Task 10/25] Current/Best: 3.12/ 18.63 GFLOPS | Progress: (20/20) | 10.27 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.57/ 15.38 GFLOPS | Progress: (4/20) | 4.08 s
[Task 11/25] Current/Best: 23.72/ 23.72 GFLOPS | Progress: (8/20) | 5.96 s
[Task 11/25] Current/Best: 22.90/ 23.72 GFLOPS | Progress: (12/20) | 8.15 s
[Task 11/25] Current/Best: 16.44/ 23.72 GFLOPS | Progress: (16/20) | 10.30 s
[Task 11/25] Current/Best: 13.29/ 23.96 GFLOPS | Progress: (20/20) | 12.26 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 4.05/ 13.33 GFLOPS | Progress: (4/20) | 7.98 s
[Task 12/25] Current/Best: 8.70/ 13.79 GFLOPS | Progress: (8/20) | 9.92 s
[Task 12/25] Current/Best: 13.18/ 17.37 GFLOPS | Progress: (12/20) | 14.02 s
[Task 12/25] Current/Best: 7.71/ 17.37 GFLOPS | Progress: (16/20) | 19.09 s
[Task 12/25] Current/Best: 20.52/ 20.52 GFLOPS | Progress: (20/20) | 28.20 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 12.06/ 12.24 GFLOPS | Progress: (4/20) | 5.38 s
[Task 13/25] Current/Best: 11.79/ 19.73 GFLOPS | Progress: (8/20) | 8.59 s
[Task 13/25] Current/Best: 11.65/ 19.73 GFLOPS | Progress: (12/20) | 11.59 s
[Task 13/25] Current/Best: 10.72/ 21.10 GFLOPS | Progress: (16/20) | 14.68 s
[Task 13/25] Current/Best: 16.29/ 23.59 GFLOPS | Progress: (20/20) | 17.12 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.34/ 12.90 GFLOPS | Progress: (4/20) | 6.17 s
[Task 14/25] Current/Best: 14.45/ 17.68 GFLOPS | Progress: (8/20) | 8.53 s
[Task 14/25] Current/Best: 8.36/ 18.10 GFLOPS | Progress: (12/20) | 11.05 s
[Task 14/25] Current/Best: 13.85/ 18.10 GFLOPS | Progress: (16/20) | 13.86 s
[Task 14/25] Current/Best: 11.22/ 18.10 GFLOPS | Progress: (20/20) | 17.18 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (4/20) | 4.24 s
[Task 15/25] Current/Best: 18.45/ 20.92 GFLOPS | Progress: (8/20) | 7.61 s
[Task 15/25] Current/Best: 15.22/ 20.92 GFLOPS | Progress: (12/20) | 8.72 s
[Task 15/25] Current/Best: 12.67/ 23.76 GFLOPS | Progress: (16/20) | 13.57 s
[Task 15/25] Current/Best: 19.29/ 23.76 GFLOPS | Progress: (20/20)
| 17.77 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 15.40/ 15.40 GFLOPS | Progress: (4/20) | 3.59 s
[Task 16/25] Current/Best: 16.55/ 16.55 GFLOPS | Progress: (8/20) | 4.99 s
[Task 16/25] Current/Best: 7.87/ 16.78 GFLOPS | Progress: (12/20) | 6.67 s
[Task 16/25] Current/Best: 3.11/ 16.78 GFLOPS | Progress: (16/20) | 8.86 s
[Task 16/25] Current/Best: 13.34/ 16.78 GFLOPS | Progress: (20/20) | 12.05 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 21.48/ 21.48 GFLOPS | Progress: (4/20) | 5.34 s
[Task 17/25] Current/Best: 23.94/ 23.94 GFLOPS | Progress: (8/20) | 7.68 s
[Task 17/25] Current/Best: 3.06/ 23.94 GFLOPS | Progress: (12/20) | 10.80 s
[Task 17/25] Current/Best: 21.52/ 23.94 GFLOPS | Progress: (16/20) | 12.77 s
[Task 17/25] Current/Best: 12.13/ 23.94 GFLOPS | Progress: (20/20) | 15.10 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 18.65/ 18.65 GFLOPS | Progress: (4/20) | 5.70 s
[Task 18/25] Current/Best: 12.36/ 18.65 GFLOPS | Progress: (8/20) | 8.63 s
[Task 18/25] Current/Best: 4.95/ 18.65 GFLOPS | Progress: (12/20) | 11.00 s
[Task 18/25] Current/Best: 10.51/ 18.65 GFLOPS | Progress: (16/20) | 14.67 s
[Task 18/25] Current/Best: 18.00/ 18.65 GFLOPS | Progress: (20/20) | 18.27 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.60/ 18.86 GFLOPS | Progress: (4/20) | 5.84 s
[Task 19/25] Current/Best: 19.69/ 20.51 GFLOPS | Progress: (8/20) | 7.84 s
[Task 19/25] Current/Best: 16.06/ 22.13 GFLOPS | Progress: (12/20) | 10.91 s
[Task 19/25] Current/Best: 16.87/ 22.13 GFLOPS | Progress: (16/20) | 13.30 s
[Task 19/25] Current/Best: 18.11/ 22.13 GFLOPS | Progress: (20/20) | 15.64 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 11.52/ 15.32 GFLOPS | Progress: (4/20) | 4.49 s
[Task 20/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (8/20) | 6.38 s
[Task 20/25] Current/Best: 15.00/ 20.26 GFLOPS | Progress: (12/20) | 9.33 s
[Task 20/25] Current/Best: 13.92/ 20.26 GFLOPS | Progress: (16/20) | 11.51 s
[Task 20/25] Current/Best: 10.80/ 20.26 GFLOPS | Progress: (20/20) | 15.54 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
- Done.
-
[Task 21/25] Current/Best: 19.18/ 19.18 GFLOPS | Progress: (4/20) | 4.39 s
[Task 21/25] Current/Best: 10.00/ 19.18 GFLOPS | Progress: (8/20) | 6.50 s
[Task 21/25] Current/Best: 16.79/ 19.90 GFLOPS | Progress: (12/20) | 9.58 s
[Task 21/25] Current/Best: 14.86/ 19.90 GFLOPS | Progress: (16/20) | 12.55 s
[Task 21/25] Current/Best: 19.15/ 19.90 GFLOPS | Progress: (20/20) | 15.11 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 3.09/ 19.89 GFLOPS | Progress: (4/20) | 4.64 s
[Task 22/25] Current/Best: 10.22/ 19.89 GFLOPS | Progress: (8/20) | 7.49 s
[Task 22/25] Current/Best: 20.52/ 20.52 GFLOPS | Progress: (12/20) | 8.78 s
[Task 22/25] Current/Best: 16.39/ 20.52 GFLOPS | Progress: (16/20) | 10.24 s
[Task 22/25] Current/Best: 6.04/ 20.52 GFLOPS | Progress: (20/20) | 13.11 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 5.36/ 23.72 GFLOPS | Progress: (4/20) | 4.33 s
[Task 23/25] Current/Best: 12.84/ 23.72 GFLOPS | Progress: (8/20) | 7.34 s
[Task 23/25] Current/Best: 5.12/ 23.72 GFLOPS | Progress: (12/20) | 10.43 s
[Task 23/25] Current/Best: 21.17/ 23.72 GFLOPS | Progress: (16/20) | 13.16 s
[Task 23/25] Current/Best: 12.53/ 23.72 GFLOPS | Progress: (20/20) | 16.00 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.21/ 8.21 GFLOPS | Progress: (4/20) | 12.60 s
[Task 24/25] Current/Best: 5.96/ 8.21 GFLOPS | Progress: (8/20) | 23.30 s
[Task 24/25] Current/Best: 1.06/ 9.20 GFLOPS | Progress: (12/20) | 33.81 s
[Task 24/25] Current/Best: 3.62/ 9.20 GFLOPS | Progress: (16/20) | 46.14 s Done.
-
[Task 24/25] Current/Best: 9.40/ 10.41 GFLOPS | Progress: (20/20) | 57.63 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 7.85/ 8.92 GFLOPS | Progress: (4/20) | 5.02 s
[Task 25/25] Current/Best: 8.40/ 8.92 GFLOPS | Progress: (8/20) | 6.33 s
[Task 25/25] Current/Best: 3.53/ 8.92 GFLOPS | Progress: (12/20) | 16.86 s
[Task 25/25] Current/Best: 9.76/ 9.76 GFLOPS | Progress: (16/20) | 27.57 s
[Task 25/25] Current/Best: 3.02/ 9.76 GFLOPS | Progress: (20/20) | 39.41 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 3.45/ 14.95 GFLOPS | Progress: (4/20) | 9.54 s
[Task 1/25] Current/Best: 12.45/ 14.95 GFLOPS | Progress: (8/20) | 13.71 s
[Task 1/25] Current/Best: 15.88/ 15.88 GFLOPS | Progress: (12/20) | 16.72 s
[Task 1/25] Current/Best: 14.53/ 17.62 GFLOPS | Progress: (16/20) | 18.86 s
[Task 1/25] Current/Best: 5.55/ 17.77 GFLOPS | Progress: (20/20) | 21.48 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 9.57/ 18.99 GFLOPS | Progress: (4/20) | 3.17 s
[Task 2/25] Current/Best: 20.52/ 20.52 GFLOPS | Progress: (8/20) | 4.54 s
[Task 2/25] Current/Best: 11.05/ 20.52 GFLOPS | Progress: (12/20) | 5.99 s
[Task 2/25] Current/Best: 5.48/ 20.52 GFLOPS | Progress: (16/20) | 7.11 s
[Task 2/25] Current/Best: 5.65/ 20.52 GFLOPS | Progress: (20/20) | 8.46 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 7.56/ 11.83 GFLOPS | Progress: (4/20) | 4.68 s
[Task 3/25] Current/Best: 19.91/ 19.91 GFLOPS | Progress: (8/20) | 6.89 s
[Task 3/25] Current/Best: 16.57/ 19.91 GFLOPS | Progress: (12/20) | 8.97 s
[Task 3/25] Current/Best: 15.63/ 19.91 GFLOPS | Progress: (16/20) | 11.28 s
[Task 3/25] Current/Best: 9.34/ 19.91 GFLOPS | Progress: (20/20) | 14.41 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.34/ 12.10 GFLOPS | Progress: (4/20) | 6.96 s
[Task 4/25] Current/Best: 6.19/ 13.03 GFLOPS | Progress: (8/20) | 8.93 s
[Task 4/25] Current/Best: 16.68/ 16.68 GFLOPS | Progress: (12/20) | 10.45 s
[Task 4/25] Current/Best: 20.75/ 20.75 GFLOPS | Progress: (16/20) | 12.42 s
[Task 4/25] Current/Best: 19.05/ 20.75 GFLOPS | Progress: (20/20) | 17.38 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 7.31/ 17.89 GFLOPS | Progress: (4/20) | 3.87 s
[Task 5/25] Current/Best: 17.31/ 18.52 GFLOPS | Progress: (8/20) | 5.29 s
[Task 5/25] Current/Best: 5.61/ 18.52 GFLOPS | Progress: (12/20) | 7.03 s
[Task 5/25] Current/Best: 13.07/ 18.52 GFLOPS | Progress: (16/20) | 9.54 s
[Task 5/25] Current/Best: 6.35/ 18.52 GFLOPS | Progress: (20/20) | 12.07 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 14.36/ 18.21 GFLOPS | Progress: (4/20) | 5.17 s
[Task 6/25] Current/Best: 15.55/ 18.21 GFLOPS | Progress: (8/20) | 9.15 s
[Task 6/25] Current/Best: 4.30/ 23.44 GFLOPS | Progress: (12/20) | 11.32 s
[Task 6/25] Current/Best: 17.79/ 23.44 GFLOPS | Progress: (16/20) | 13.98 s
[Task 6/25] Current/Best: 6.22/ 23.44 GFLOPS | Progress: (20/20) | 16.45 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.63/ 22.86 GFLOPS | Progress: (4/20) | 4.77 s
[Task 7/25] Current/Best: 8.76/ 22.86 GFLOPS | Progress: (8/20) | 7.21 s
[Task 7/25] Current/Best: 14.23/ 22.86 GFLOPS | Progress: (12/20) | 9.44 s
[Task 7/25] Current/Best: 12.33/ 22.86 GFLOPS | Progress: (16/20) | 11.81 s
[Task 7/25] Current/Best: 12.21/ 22.86 GFLOPS | Progress: (20/20) | 13.75 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 15.61/ 15.61 GFLOPS | Progress: (4/20) | 4.12 s
[Task 8/25] Current/Best: 4.19/ 15.61 GFLOPS | Progress: (8/20) | 6.83 s
[Task 8/25] Current/Best: 9.46/ 15.61 GFLOPS | Progress: (12/20) | 15.48 s
[Task 8/25] Current/Best: 4.21/ 17.90 GFLOPS | Progress: (16/20) | 24.62 s
[Task 8/25] Current/Best: 5.20/ 17.90 GFLOPS | Progress: (20/20) | 31.35 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 10.45/ 19.85 GFLOPS | Progress: (4/20) | 3.92 s
[Task 9/25] Current/Best: 6.61/ 19.85 GFLOPS | Progress: (8/20) | 5.95 s
[Task 9/25] Current/Best: 7.92/ 20.80 GFLOPS | Progress: (12/20) | 7.77 s
[Task 9/25] Current/Best: 11.30/ 20.80 GFLOPS | Progress: (16/20) | 9.66 s
[Task 9/25] Current/Best: 10.01/ 20.80 GFLOPS | Progress: (20/20) | 16.83 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 14.09/ 14.97 GFLOPS | Progress: (4/20) | 3.37 s
[Task 10/25] Current/Best: 16.16/ 18.20 GFLOPS | Progress: (8/20) | 5.44 s
[Task 10/25] Current/Best: 3.98/ 18.20 GFLOPS | Progress: (12/20) | 7.17 s
[Task 10/25] Current/Best: 9.58/ 18.20 GFLOPS | Progress: (16/20) | 9.86 s
[Task 10/25] Current/Best: 5.30/ 22.40 GFLOPS | Progress: (20/20) | 12.57 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 16.22/ 16.22 GFLOPS | Progress: (4/20) | 4.94 s
[Task 11/25] Current/Best: 15.90/ 23.76 GFLOPS | Progress: (8/20) | 6.84 s
[Task 11/25] Current/Best: 16.55/ 23.95 GFLOPS | Progress: (12/20) | 8.55 s
[Task 11/25] Current/Best: 21.13/ 23.95 GFLOPS | Progress: (16/20) | 10.67 s
[Task 11/25] Current/Best: 6.26/ 23.95 GFLOPS | Progress: (20/20) | 12.79 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 5.29/ 15.67 GFLOPS | Progress: (4/20) | 4.45 s
[Task 12/25] Current/Best: 13.27/ 16.23 GFLOPS | Progress: (8/20) | 6.64 s
[Task 12/25] Current/Best: 11.09/ 16.23 GFLOPS | Progress: (12/20) | 9.95 s
[Task 12/25] Current/Best: 10.30/ 20.31 GFLOPS | Progress: (16/20) | 18.32 s
[Task 12/25] Current/Best: 12.47/ 20.31 GFLOPS | Progress: (20/20) | 21.78 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 2.96/ 9.35 GFLOPS | Progress: (4/20) | 5.56 s
[Task 13/25] Current/Best: 6.10/ 11.64 GFLOPS | Progress: (8/20) | 8.54 s
[Task 13/25] Current/Best: 15.80/ 16.10 GFLOPS | Progress: (12/20) | 10.40 s
[Task 13/25] Current/Best: 3.57/ 20.60 GFLOPS | Progress: (16/20) | 12.85 s
[Task 13/25] Current/Best: 15.23/ 20.60 GFLOPS | Progress: (20/20) | 15.08 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.90/ 12.90 GFLOPS | Progress: (4/20) | 6.59 s
[Task 14/25] Current/Best: 7.11/ 12.90 GFLOPS | Progress: (8/20) | 10.76 s
[Task 14/25] Current/Best: 9.37/ 12.90 GFLOPS | Progress: (12/20) | 14.08 s
[Task 14/25] Current/Best: 16.29/ 16.29 GFLOPS | Progress: (16/20) | 20.36 s
[Task 14/25] Current/Best: 14.06/ 16.29 GFLOPS | Progress: (20/20) | 25.85 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 11.76/ 18.00 GFLOPS | Progress: (4/20) | 5.91 s
[Task 15/25] Current/Best: 17.50/ 18.79 GFLOPS | Progress: (8/20) | 10.83 s
[Task 15/25] Current/Best: 23.33/ 23.33 GFLOPS | Progress: (12/20) | 12.57 s
[Task 15/25] Current/Best: 18.20/ 23.33 GFLOPS | Progress: (16/20) | 13.84 s
[Task 15/25] Current/Best: 20.80/ 23.33 GFLOPS | Progress: (20/
20) | 16.60 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 13.98/ 19.00 GFLOPS | Progress: (4/20) | 3.49 s
[Task 16/25] Current/Best: 16.10/ 19.00 GFLOPS | Progress: (8/20) | 5.67 s
[Task 16/25] Current/Best: 12.83/ 19.00 GFLOPS | Progress: (12/20) | 8.88 s
[Task 16/25] Current/Best: 9.80/ 19.00 GFLOPS | Progress: (16/20) | 11.27 s
[Task 16/25] Current/Best: 1.58/ 19.00 GFLOPS | Progress: (20/20) | 13.69 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 1.56/ 18.87 GFLOPS | Progress: (4/20) | 5.84 s
[Task 17/25] Current/Best: 9.59/ 18.87 GFLOPS | Progress: (8/20) | 8.30 s
[Task 17/25] Current/Best: 11.69/ 18.87 GFLOPS | Progress: (12/20) | 11.28 s
[Task 17/25] Current/Best: 16.06/ 23.00 GFLOPS | Progress: (16/20) | 13.26 s
[Task 17/25] Current/Best: 6.28/ 23.00 GFLOPS | Progress: (20/20) | 15.59 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.95/ 18.06 GFLOPS | Progress: (4/20) | 5.03 s
[Task 18/25] Current/Best: 10.09/ 18.06 GFLOPS | Progress: (8/20) | 7.62 s
[Task 18/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (12/20) | 10.04 s
[Task 18/25] Current/Best: 19.14/ 19.14 GFLOPS | Progress: (16/20) | 14.57 s
[Task 18/25] Current/Best: 14.92/ 19.14 GFLOPS | Progress: (20/20) | 19.18 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.62/ 21.62 GFLOPS | Progress: (4/20) | 3.99 s
[Task 19/25] Current/Best: 12.14/ 21.62 GFLOPS | Progress: (8/20) | 7.33 s
[Task 19/25] Current/Best: 22.53/ 22.53 GFLOPS | Progress: (12/20) | 9.66 s
[Task 19/25] Current/Best: 10.57/ 22.53 GFLOPS | Progress: (16/20) | 14.09 s
[Task 19/25] Current/Best: 12.89/ 22.53 GFLOPS | Progress: (20/20) | 16.76 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 6.67/ 18.64 GFLOPS | Progress: (4/20) | 5.11 s
[Task 20/25] Current/Best: 7.65/ 18.64 GFLOPS | Progress: (8/20) | 7.72 s
[Task 20/25] Current/Best: 10.43/ 20.20 GFLOPS | Progress: (12/20) | 9.98 s
[Task 20/25] Current/Best: 5.35/ 20.20 GFLOPS | Progress: (16/20) | 11.61 s Done.
+
[Task 20/25] Current/Best: 14.01/ 20.20 GFLOPS | Progress: (20/20) | 13.96 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 9.35/ 20.43 GFLOPS | Progress: (4/20) | 4.42 s
[Task 21/25] Current/Best: 10.65/ 20.43 GFLOPS | Progress: (8/20) | 6.99 s
[Task 21/25] Current/Best: 10.66/ 20.43 GFLOPS | Progress: (12/20) | 9.41 s
[Task 21/25] Current/Best: 7.14/ 20.43 GFLOPS | Progress: (16/20) | 13.05 s
[Task 21/25] Current/Best: 10.69/ 21.46 GFLOPS | Progress: (20/20) | 15.53 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.69/ 20.70 GFLOPS | Progress: (4/20) | 4.30 s
[Task 22/25] Current/Best: 10.63/ 20.70 GFLOPS | Progress: (8/20) | 6.56 s
[Task 22/25] Current/Best: 19.21/ 20.70 GFLOPS | Progress: (12/20) | 8.68 s
[Task 22/25] Current/Best: 15.53/ 20.70 GFLOPS | Progress: (16/20)
| 10.63 s
[Task 22/25] Current/Best: 16.46/ 22.52 GFLOPS | Progress: (20/20) | 12.03 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 18.49/ 20.20 GFLOPS | Progress: (4/20) | 4.49 s
[Task 23/25] Current/Best: 17.79/ 20.20 GFLOPS | Progress: (8/20) | 6.77 s
[Task 23/25] Current/Best: 12.02/ 20.20 GFLOPS | Progress: (12/20) | 9.27 s
[Task 23/25] Current/Best: 11.57/ 20.20 GFLOPS | Progress: (16/20) | 15.98 s
[Task 23/25] Current/Best: 15.25/ 20.20 GFLOPS | Progress: (20/20) | 18.16 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.52/ 5.60 GFLOPS | Progress: (4/20) | 7.92 s
[Task 24/25] Current/Best: 8.16/ 8.16 GFLOPS | Progress: (8/20) | 18.70 s
[Task 24/25] Current/Best: 7.02/ 8.16 GFLOPS | Progress: (12/20) | 30.28 s
[Task 24/25] Current/Best: 7.16/ 8.16 GFLOPS | Progress: (16/20) | 42.30 s Done.
+
[Task 24/25] Current/Best: 3.57/ 9.35 GFLOPS | Progress: (20/20) | 44.61 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 3.02/ 5.93 GFLOPS | Progress: (4/20) | 3.47 s
[Task 25/25] Current/Best: 7.81/ 7.81 GFLOPS | Progress: (8/20) | 4.59 s
[Task 25/25] Current/Best: 3.66/ 7.81 GFLOPS | Progress: (12/20) | 15.07 s
[Task 25/25] Current/Best: 3.04/ 7.94 GFLOPS | Progress: (16/20) | 24.46 s
[Task 25/25] Current/Best: 5.12/ 7.94 GFLOPS | Progress: (20/20) | 34.95 s
@@ -731,8 +730,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 399.06583912000315, 'median': 399.02644880000935, 'std': 0.7040027068698534}
- unoptimized: {'mean': 510.9940208499984, 'median': 510.723029199994, 'std': 1.8448765714679003}
+ optimized: {'mean': 406.61466848996497, 'median': 406.4667856499909, 'std': 0.7957493914243219}
+ unoptimized: {'mean': 517.7567010299754, 'median': 517.5474089998715, 'std': 2.42827195278956}
@@ -755,7 +754,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 7.293 seconds)
+ **Total running time of the script:** ( 11 minutes 7.036 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 14a8de5805..a2b2825eb0 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
- 1.419e-07 secs/op
+ 1.32e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 5d184b96ad..7f48f8b133 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, 0x1200c780)), stage(b, placeholder(b, 0x21ac2e70)), 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, 0x2332ba20)), stage(b, placeholder(b, 0xea57950)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 7485178c25..f52d481245 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:10.838** total execution time for **tutorial** files:
+**14:13.250** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:07.293 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:07.036 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:11.808 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:08.636 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.842 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.435 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.189 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.540 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:16.297 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:20.941 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.704 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.781 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.544 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.717 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.153 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.154 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 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_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :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 7ee47ac210..f8dd87a11c 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,8 +294,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
- naive: 0.000007
+ Numpy running time: 0.000012
+ naive: 0.000017
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000007
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.9694500007244646e-06 1.0
- naive 6.6887e-06 0.9597170507435622
- parallel 7.9686e-06 1.1433613842084633
- vector 2.46075e-05 3.530766415921211
+ numpy 1.1677980000968092e-05 1.0
+ naive 1.68656e-05 1.444222373955244
+ parallel 6.9642999999999995e-06 0.596361699491065
+ vector 2.4532200000000002e-05 2.1007228988203703
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018872
+ Numpy running time: 0.018971
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.406899
+ none: 3.441213
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.302790
+ blocking: 0.311520
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.331970
+ vectorization: 0.331753
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116988
+ loop permutation: 0.118850
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108325
+ array packing: 0.108036
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110173
+ block caching: 0.110545
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146266
+ parallelization: 0.146347
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4068992531000006 1.0
- blocking 0.302790432 0.08887566361831374
- vectorization 0.33196982979999995 0.09744045982514289
- loop permutation 0.11698826600000001 0.03433863384529209
- array packing 0.10832488900000001 0.03179574180288225
- block caching 0.11017343589999999 0.032338331049781156
- parallelization 0.1462656897 0.04293220281371988
+ none 3.441213220900001 1.0
+ blocking 0.3115195103 0.0905260704009868
+ vectorization 0.3317532897 0.09640590931277272
+ loop permutation 0.1188499132 0.03453721277082519
+ array packing 0.108035711 0.031394657658482664
+ block caching 0.110544785 0.032123782487121964
+ parallelization 0.1463471308 0.04252777186579708
@@ -1663,7 +1663,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.842 seconds)
+ **Total running time of the script:** ( 1 minutes 1.435 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 2091fe5d67..5c00525a3a 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-9a451411650905866822cc79bd3365942d5dd9d1
+3e3d900c66ba8caad6b491c60d1331be470f9cba
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index ff5aee201d..2b1bf098eb 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -572,7 +572,7 @@ 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 10.817 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.226 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index c2c8d0fe34..c99347cb7d 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -493,7 +493,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 934ms/step
+1/1 [==============================] - 1s 967ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 7c9f0f930e..40990222a2 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.zipa22a691e-31fc-4b6c-8680-46f0dbf2d894 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.zip685dce34-3af5-43ef-a312-c19e66a53b4b 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 726d0a8d12..4926111af3 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -435,13 +435,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 51.5MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 55.2MB/s]
- 47%|####7 | 19.7M/41.5M [00:00<00:00, 54.9MB/s]
- 60%|###### | 24.9M/41.5M [00:00<00:00, 46.2MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 45.3MB/s]
- 90%|########9 | 37.2M/41.5M [00:00<00:00, 43.2MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 47.1MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 41.2MB/s]
+ 25%|##4 | 10.3M/41.5M [00:00<00:00, 33.4MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 33.8MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 46.6MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 51.5MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 46.3MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 44.9MB/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 382507f613..1f2b9123ce 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 35%|###4 | 15.6M/44.7M [00:00<00:00, 163MB/s]
- 74%|#######3 | 32.9M/44.7M [00:00<00:00, 174MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 188MB/s]
+ 39%|###8 | 17.4M/44.7M [00:00<00:00, 182MB/s]
+ 85%|########4 | 38.0M/44.7M [00:00<00:00, 202MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 206MB/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 b59b010423..ff592a870f 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -632,7 +632,7 @@ 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 9.976 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.438 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 c7a86fe699..fcf5b1c958 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>05:35.178</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:43.845</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:10.817</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:14.438</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:09.976</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:11.226</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>00:45.592</p></td>
+<td><p>00:46.162</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>00:30.234</p></td>
+<td><p>00:31.080</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>00:27.731</p></td>
+<td><p>00:28.126</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>00:25.946</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
+<td><p>00:25.674</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>00:25.140</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:24.916</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>00:22.122</p></td>
+<td><p>00:22.375</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:15.128</p></td>
+<td><p>00:17.368</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>00:02.491</p></td>
+<td><p>00:02.481</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 deb0627d6d..d7f34161a8 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -649,7 +649,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.8856 15.8379 16.1727 15.8223 0.1016
+ 16.1504 16.1103 16.4735 15.9836 0.1280
</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 22c2752158..55c9570025 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,42 +436,21 @@ 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%|2 | 3.94M/170M [00:00<00:04, 41.1MB/s]
- 6%|5 | 9.88M/170M [00:00<00:03, 53.4MB/s]
- 9%|8 | 15.0M/170M [00:00<00:03, 52.9MB/s]
- 12%|#1 | 20.0M/170M [00:00<00:03, 49.7MB/s]
- 15%|#4 | 24.8M/170M [00:00<00:03, 44.7MB/s]
- 17%|#7 | 29.1M/170M [00:00<00:03, 40.5MB/s]
- 20%|#9 | 33.8M/170M [00:00<00:03, 42.9MB/s]
- 23%|##2 | 38.8M/170M [00:00<00:03, 45.5MB/s]
- 26%|##6 | 44.2M/170M [00:00<00:02, 48.8MB/s]
- 29%|##8 | 48.9M/170M [00:01<00:02, 46.0MB/s]
- 31%|###1 | 53.4M/170M [00:01<00:02, 44.3MB/s]
- 34%|###3 | 57.7M/170M [00:01<00:02, 42.6MB/s]
- 36%|###6 | 61.8M/170M [00:01<00:02, 42.5MB/s]
- 39%|###8 | 65.9M/170M [00:01<00:02, 42.6MB/s]
- 42%|####1 | 70.8M/170M [00:01<00:02, 45.2MB/s]
- 44%|####4 | 75.2M/170M [00:01<00:02, 44.5MB/s]
- 47%|####6 | 79.5M/170M [00:01<00:02, 44.5MB/s]
- 49%|####9 | 83.8M/170M [00:01<00:02, 42.0MB/s]
- 52%|#####1 | 87.8M/170M [00:02<00:02, 41.6MB/s]
- 55%|#####4 | 93.4M/170M [00:02<00:01, 46.4MB/s]
- 58%|#####7 | 97.9M/170M [00:02<00:01, 44.6MB/s]
- 60%|###### | 103M/170M [00:02<00:01, 46.3MB/s]
- 63%|######3 | 108M/170M [00:02<00:01, 47.8MB/s]
- 66%|######6 | 112M/170M [00:02<00:01, 48.4MB/s]
- 69%|######8 | 117M/170M [00:02<00:01, 40.6MB/s]
- 71%|#######1 | 121M/170M [00:02<00:01, 39.3MB/s]
- 75%|#######4 | 127M/170M [00:02<00:01, 44.0MB/s]
- 78%|#######7 | 132M/170M [00:03<00:00, 46.6MB/s]
- 81%|######## | 138M/170M [00:03<00:00, 50.2MB/s]
- 84%|########3 | 142M/170M [00:03<00:00, 45.3MB/s]
- 87%|########7 | 148M/170M [00:03<00:00, 49.6MB/s]
- 90%|######### | 153M/170M [00:03<00:00, 46.9MB/s]
- 93%|#########2| 158M/170M [00:03<00:00, 47.0MB/s]
- 96%|#########5| 162M/170M [00:03<00:00, 44.4MB/s]
- 99%|#########9| 168M/170M [00:03<00:00, 49.1MB/s]
-100%|##########| 170M/170M [00:03<00:00, 45.5MB/s]
+ 3%|2 | 4.36M/170M [00:00<00:03, 45.2MB/s]
+ 6%|6 | 11.0M/170M [00:00<00:02, 59.4MB/s]
+ 17%|#6 | 28.0M/170M [00:00<00:01, 114MB/s]
+ 23%|##3 | 39.8M/170M [00:00<00:01, 117MB/s]
+ 33%|###2 | 55.2M/170M [00:00<00:00, 133MB/s]
+ 42%|####2 | 71.4M/170M [00:00<00:00, 145MB/s]
+ 50%|##### | 85.2M/170M [00:00<00:00, 93.5MB/s]
+ 57%|#####6 | 96.2M/170M [00:01<00:00, 81.0MB/s]
+ 62%|######2 | 106M/170M [00:01<00:00, 82.3MB/s]
+ 67%|######7 | 114M/170M [00:01<00:00, 67.1MB/s]
+ 72%|#######1 | 122M/170M [00:01<00:00, 66.5MB/s]
+ 79%|#######9 | 135M/170M [00:01<00:00, 80.9MB/s]
+ 88%|########8 | 150M/170M [00:01<00:00, 100MB/s]
+ 96%|#########6| 163M/170M [00:01<00:00, 109MB/s]
+100%|##########| 170M/170M [00:01<00:00, 96.5MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-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)
/venv/apache-tvm-py3.7/lib/python3.7/site-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=& [...]
@@ -569,7 +548,7 @@ 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 15.737 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 15.688 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 4e4503d85b..9048010833 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,9 +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]
- 31%|###1 | 4.24M/13.6M [00:00<00:00, 44.5MB/s]
- 65%|######4 | 8.76M/13.6M [00:00<00:00, 46.2MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 65.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 182MB/s]
</pre></div>
</div>
</div>
@@ -573,7 +571,7 @@ 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)
- 90.4501 90.3762 94.1002 90.1241 0.4277
+ 90.5989 90.3383 106.4143 90.1573 1.6540
</pre></div>
</div>
<div class="admonition note">
@@ -612,7 +610,7 @@ 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 19.573 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.100 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 03a5718f52..636892f979 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -569,7 +569,7 @@ 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)
- 121.4551 121.1747 126.9564 120.3551 1.0368
+ 120.9381 120.9379 122.1887 119.9629 0.3998
</pre></div>
</div>
<div class="admonition note">
@@ -597,7 +597,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 1.895 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 0.644 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 b0e0890df3..46b8b4af83 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -507,7 +507,7 @@ 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 34.178 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.106 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 2831445258..d7c1e7f245 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -449,24 +449,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|2 | 3453/132723 [00:00<00:03, 34483.01KB/s]
- 8%|7 | 10043/132723 [00:00<00:02, 52949.32KB/s]
- 13%|#3 | 17680/132723 [00:00<00:01, 63637.40KB/s]
- 19%|#9 | 25395/132723 [00:00<00:01, 68966.26KB/s]
- 25%|##4 | 33016/132723 [00:00<00:01, 71575.53KB/s]
- 31%|### | 40746/132723 [00:00<00:01, 73518.37KB/s]
- 37%|###6 | 48455/132723 [00:00<00:01, 74681.30KB/s]
- 42%|####2 | 56197/132723 [00:00<00:01, 75550.84KB/s]
- 48%|####8 | 63906/132723 [00:00<00:00, 76025.18KB/s]
- 54%|#####3 | 71509/132723 [00:01<00:00, 75793.14KB/s]
- 60%|#####9 | 79089/132723 [00:01<00:00, 75628.58KB/s]
- 65%|######5 | 86653/132723 [00:01<00:00, 75352.89KB/s]
- 71%|####### | 94189/132723 [00:01<00:00, 75144.66KB/s]
- 77%|#######6 | 101810/132723 [00:01<00:00, 75453.21KB/s]
- 83%|########2 | 109509/132723 [00:01<00:00, 75911.56KB/s]
- 88%|########8 | 117271/132723 [00:01<00:00, 76420.57KB/s]
- 94%|#########4| 125094/132723 [00:01<00:00, 76961.06KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 73584.24KB/s]
+ 3%|3 | 4406/132723 [00:00<00:02, 44057.31KB/s]
+ 10%|9 | 12776/132723 [00:00<00:01, 67372.59KB/s]
+ 16%|#6 | 21346/132723 [00:00<00:01, 75737.75KB/s]
+ 23%|##2 | 29917/132723 [00:00<00:01, 79671.89KB/s]
+ 29%|##8 | 38446/132723 [00:00<00:01, 81695.28KB/s]
+ 35%|###5 | 46933/132723 [00:00<00:01, 82770.23KB/s]
+ 42%|####1 | 55537/132723 [00:00<00:00, 83837.84KB/s]
+ 48%|####8 | 64108/132723 [00:00<00:00, 84430.69KB/s]
+ 55%|#####4 | 72713/132723 [00:00<00:00, 84928.93KB/s]
+ 61%|######1 | 81273/132723 [00:01<00:00, 85127.71KB/s]
+ 68%|######7 | 89894/132723 [00:01<00:00, 85456.62KB/s]
+ 74%|#######4 | 98516/132723 [00:01<00:00, 85687.10KB/s]
+ 81%|######## | 107163/132723 [00:01<00:00, 85921.67KB/s]
+ 87%|########7 | 115791/132723 [00:01<00:00, 86027.69KB/s]
+ 94%|#########3| 124394/132723 [00:01<00:00, 85955.34KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83011.90KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -505,7 +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 52.476 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 51.090 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 838e084157..6cde0b65c2 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>12:29.276</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:26.900</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>03:15.737</p></td>
+<td><p>03:15.688</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>02:52.476</p></td>
+<td><p>02:51.090</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:01.895</p></td>
+<td><p>02:00.644</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>01:34.178</p></td>
+<td><p>01:33.106</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>01:19.573</p></td>
+<td><p>01:20.100</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>00:35.473</p></td>
+<td><p>00:36.154</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.223</p></td>
+<td><p>00:25.209</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.713</p></td>
+<td><p>00:24.902</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 46d6f5d5b6..7870c56f1e 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -608,7 +608,7 @@ 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.zipb112a9ba-dd2d-45e2-b293-671dfb3805f6 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.zipb93788b8-dfeb-4af6-aaba-3f2f10d0f519 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 c24076b3db..544ff8a39e 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>00:45.251</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:45.193</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="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>00:41.806</p></td>
+<td><p>00:41.855</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>00:02.419</p></td>
+<td><p>00:02.338</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.017</p></td>
+<td><p>00:00.993</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 27b8c2ba86..66f94f3aba 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: 6915us [6915us] (45.65%; 45.65%)
-FoldScaleAxis: 8232us [7us] (54.35%; 54.35%)
- FoldConstant: 8225us [1724us] (54.30%; 99.91%)
- InferType: 6500us [6500us] (42.91%; 79.04%)
+InferType: 6743us [6743us] (46.16%; 46.16%)
+FoldScaleAxis: 7866us [5us] (53.84%; 53.84%)
+ FoldConstant: 7861us [1606us] (53.81%; 99.94%)
+ InferType: 6255us [6255us] (42.82%; 79.57%)
</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: 6528us [6528us] (44.66%; 44.66%)
-FoldScaleAxis: 8089us [6us] (55.34%; 55.34%)
- FoldConstant: 8083us [1735us] (55.30%; 99.93%)
- InferType: 6348us [6348us] (43.43%; 78.53%)
+InferType: 6279us [6279us] (44.43%; 44.43%)
+FoldScaleAxis: 7853us [4us] (55.57%; 55.57%)
+ FoldConstant: 7848us [1606us] (55.54%; 99.94%)
+ InferType: 6242us [6242us] (44.17%; 79.54%)
</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 ab7b325970..4d3bb7356c 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 50.151966 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.024513 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 ab90118904..b26185f8a2 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: 13.346815 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.029952 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 24370f5191..a0a943d90d 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: 0.018818
-Baseline: 3.422008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019078
+Baseline: 3.463612
</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: 0.310735
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.309250
</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: 0.343904
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.342270
</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: 0.116739
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.121195
</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: 0.109420
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109486
</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: 0.111505
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111077
</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: 0.148249
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147532
</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 0098ce04a8..6cbd43f5c8 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>00:35.229</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.323</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>00:32.615</p></td>
+<td><p>00:32.757</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>00:01.430</p></td>
+<td><p>00:01.417</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.183</p></td>
+<td><p>00:01.150</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 6ba6401560..d5cbdc64c8 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>06:41.239</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:54.408</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>03:26.432</p></td>
+<td><p>03:42.823</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>01:30.415</p></td>
+<td><p>01:30.060</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>00:59.818</p></td>
+<td><p>00:59.349</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>00:23.100</p></td>
+<td><p>00:21.234</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>00:10.924</p></td>
+<td><p>00:10.611</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>00:10.550</p></td>
+<td><p>00:10.330</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 43c565abf6..e0f9498dc9 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
@@ -491,109 +491,483 @@ 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, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_2: int32 = (rc.outer.outer*72)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 96)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_2 < 328), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 96)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- }
- for (rc.outer.inner: int32, 0, 8) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 96)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 97)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 98)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 99)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 100)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 101)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 102)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 103)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 104)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 105)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 106)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 107)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 192)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 288)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 193)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 289)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 194)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 290)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 195)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 291)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 196)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 292)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 197)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 293)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 198)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 294)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 199)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 295)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 200)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 296)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 201)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 297)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 202)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 298)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 203)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*384) + (rc.outer.inner*12)) + 299)]))
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -630,7 +1004,7 @@ 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: 0.292 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.356 ms
</pre></div>
</div>
</div>
@@ -659,36 +1033,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+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=8)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_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=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
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=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_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_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
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)
@@ -708,14 +1082,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
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=392)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -733,90 +1107,430 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[2016];
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
__shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[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) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 56) {
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 40) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- if (((int)threadIdx.x) < 328) {
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 96)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 97)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 98)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 99)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 100)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 101)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 102)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 103)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 104)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 106)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 107)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 192)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 288)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 193)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 289)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 194)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 290)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 195)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 291)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 196)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 292)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 197)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 293)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 198)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 294)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 199)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 295)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 200)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 296)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 201)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 297)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 202)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 298)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 203)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 49) * 384) + (rc_outer_inner * 12)) + 299)]));
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -853,7 +1567,7 @@ 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 26.432 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 42.823 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 91b8c2d0fa..b5862f6bf1 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -902,7 +902,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2002 8.1987 8.2049 8.1970 0.0034
+ 8.1801 8.1762 8.1909 8.1731 0.0078
</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 f53a99b6dc..66d34d5f45 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -921,7 +921,7 @@ 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)
- 751.4023 751.0141 752.3609 750.8318 0.6819
+ 750.4536 747.6420 756.7698 746.9488 4.4752
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ 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 30.415 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.060 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 1e7a50bada..9db0bd8474 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,104 +625,80 @@ 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], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [256], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
- {
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_4: int32 = (i.inner*16)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_5: int32 = ((i.inner*16) + 1)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_6: int32 = ((i.inner*16) + 2)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_7: int32 = ((i.inner*16) + 3)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_8: int32 = ((i.inner*16) + 4)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_9: int32 = ((i.inner*16) + 5)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_10: int32 = ((i.inner*16) + 6)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_11: int32 = ((i.inner*16) + 7)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_12: int32 = ((i.inner*16) + 8)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_13: int32 = ((i.inner*16) + 9)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_14: int32 = ((i.inner*16) + 10)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_15: int32 = ((i.inner*16) + 11)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_16: int32 = ((i.inner*16) + 12)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_17: int32 = ((i.inner*16) + 13)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_18: int32 = ((i.inner*16) + 14)
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_19: int32 = ((i.inner*16) + 15)
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*4096) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 128) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ }
}
}
}
@@ -760,7 +736,7 @@ 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: 1.947 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.721 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 0f47e7da4f..0565bbb881 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>00:34.736</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:30.749</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</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>00:34.699</p></td>
+<td><p>00:30.710</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.023</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</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="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>
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 f3c3f56a6a..ec7b281a4c 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -557,7 +557,8 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+No: 1 GFLOPS: 35.55/35.55 result: MeasureResult(costs=(0.006511551764705883,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9945309162139893, timestamp=1664473011.6994371) [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5279801
+No: 2 GFLOPS: 0.00/35.55 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
@@ -679,8 +680,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10036027
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5392612
+No: 3 GFLOPS: 0.00/35.55 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
@@ -802,9 +803,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,449385
-No: 3 GFLOPS: 2.49/2.49 result: MeasureResult(costs=(0.0929771955,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.139984130859375, timestamp=1664462703.714772) [('tile_f', [-1, 16, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4076520
-No: 4 GFLOPS: 0.00/2.49 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8305955
+No: 4 GFLOPS: 7.41/35.55 result: MeasureResult(costs=(0.03122363275,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.096970558166504, timestamp=1664473014.987342) [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2277513
+No: 5 GFLOPS: 8.11/35.55 result: MeasureResult(costs=(0.02855320725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4308624267578125, timestamp=1664473017.5918832) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8098924
+No: 6 GFLOPS: 0.00/35.55 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
@@ -926,8 +928,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7861778
-No: 5 GFLOPS: 0.00/2.49 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9320977
+No: 7 GFLOPS: 0.00/35.55 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
@@ -1049,8 +1051,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10025787
-No: 6 GFLOPS: 0.00/2.49 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8195926
+No: 8 GFLOPS: 0.00/35.55 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
@@ -1172,8 +1174,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6963541
-No: 7 GFLOPS: 0.00/2.49 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5484152
+No: 9 GFLOPS: 0.00/35.55 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
@@ -1295,9 +1297,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3646517
-No: 8 GFLOPS: 83.95/83.95 result: MeasureResult(costs=(0.002757704589285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8263216018676758, timestamp=1664462708.1927118) [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1841668
-No: 9 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4868236
+No: 10 GFLOPS: 0.00/35.55 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
@@ -1419,8 +1420,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7607118
-No: 10 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9837459
+No: 11 GFLOPS: 50.45/50.45 result: MeasureResult(costs=(0.004589104045454546,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2390820980072021, timestamp=1664473020.2844932) [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5619283
+No: 12 GFLOPS: 0.00/50.45 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
@@ -1542,8 +1544,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9825760
-No: 11 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,471114
+No: 13 GFLOPS: 0.00/50.45 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
@@ -1665,8 +1667,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9264322
-No: 12 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4158613
+No: 14 GFLOPS: 0.00/50.45 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
@@ -1788,8 +1790,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10155113
-No: 13 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6504711
+No: 15 GFLOPS: 354.13/354.13 result: MeasureResult(costs=(0.0006537152418300654,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.526313304901123, timestamp=1664473022.0321066) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7067967
+No: 16 GFLOPS: 0.00/354.13 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
@@ -1911,8 +1914,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3935020
-No: 14 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4314821
+No: 17 GFLOPS: 0.00/354.13 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
@@ -2034,8 +2037,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4239545
-No: 15 GFLOPS: 0.00/83.95 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9077245
+No: 18 GFLOPS: 0.00/354.13 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
@@ -2157,9 +2160,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2663478
-No: 16 GFLOPS: 88.06/88.06 result: MeasureResult(costs=(0.0026287926721311476,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3867878913879395, timestamp=1664462710.0466747) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1018709
-No: 17 GFLOPS: 0.00/88.06 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7688802
+No: 19 GFLOPS: 68.68/354.13 result: MeasureResult(costs=(0.003370504290322581,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8591158390045166, timestamp=1664473024.0965714) [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9103762
+No: 20 GFLOPS: 0.00/354.13 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
@@ -2281,132 +2284,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,329649
-No: 18 GFLOPS: 2.97/88.06 result: MeasureResult(costs=(0.07805895225000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.844818115234375, timestamp=1664462715.0883167) [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7952100
-No: 19 GFLOPS: 0.00/88.06 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
- func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 227, in build
- input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
- return ffi.lower_schedule(inp, args, name, binds, simple_mode)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4791464
-No: 20 GFLOPS: 332.34/332.34 result: MeasureResult(costs=(0.0006965726736111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3543648719787598, timestamp=1664462715.7876148) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3746622
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9975019
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2445,9 +2323,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3746622
+[('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7067967
Finish loading 20 records
-Time cost of this operator: 0.001133
+Time cost of this operator: 0.001007
</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 4b70fa4321..a6dc8cfc86 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -582,10 +582,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.4 98.721 (1, 2, 10, 10, 3) 2 1 [309.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.056 0.975 (1, 6, 10, 10) 1 1 [3.056]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.304 (1, 1, 10, 10, 3) 1 1 [0.954]
-Total_time - 313.41 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.5 98.724 (1, 2, 10, 10, 3) 2 1 [312.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.078 0.972 (1, 6, 10, 10) 1 1 [3.078]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.304 (1, 1, 10, 10, 3) 1 1 [0.962]
+Total_time - 316.54 - - - - -
</pre></div>
</div>
</div>
@@ -636,13 +636,12 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.4 97.999 (1, 6, 10, 10, 1) 2 1 [134.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.764 1.286 (1, 6, 10, 10) 1 1 [1.764]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.98 0.714 (1, 1, 10, 10, 3) 1 1 [0.98]
-Total_time - 137.144 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.8 97.468 (1, 6, 10, 10, 1) 2 1 [102.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.825 1.73 (1, 6, 10, 10) 1 1 [1.825]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.846 0.802 (1, 3, 10, 10, 1) 1 1 [0.846]
+Total_time - 105.471 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.033 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/9ccca8fd489a1486ac71b55a55c320c5/micro_autotune.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_autotune.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 3b47530684..3d65fb3734 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/tmpaovt4iji/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpe_uga4xj/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [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/tmpaovt4iji/images/target contains 8144 images
-/tmp/tmpaovt4iji/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [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/tmpe_uga4xj/images/target contains 8144 images
+/tmp/tmpe_uga4xj/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 - 47s - loss: 0.2246 - accuracy: 0.9222 - val_loss: 0.1557 - val_accuracy: 0.9452 - 47s/epoch - 143ms/step
+328/328 - 47s - loss: 0.2292 - accuracy: 0.9242 - val_loss: 0.1456 - val_accuracy: 0.9551 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0998 - accuracy: 0.9643 - val_loss: 0.1059 - val_accuracy: 0.9634 - 43s/epoch - 131ms/step
+328/328 - 44s - loss: 0.0946 - accuracy: 0.9665 - val_loss: 0.1179 - val_accuracy: 0.9607 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0675 - accuracy: 0.9751 - val_loss: 0.1475 - val_accuracy: 0.9502 - 43s/epoch - 131ms/step
+328/328 - 44s - loss: 0.0694 - accuracy: 0.9743 - val_loss: 0.0980 - val_accuracy: 0.9596 - 44s/epoch - 133ms/step
-<keras.callbacks.History object at 0x7f1cf88238d0>
+<keras.callbacks.History object at 0x7f5ab1ae3ed0>
</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 7.924 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 12.192 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 97c11b0a2c..312cf57fde 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>06:23.049</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:25.769</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>05:07.924</p></td>
+<td><p>05:12.192</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>01:00.033</p></td>
+<td><p>00:59.602</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>00:10.663</p></td>
+<td><p>00:09.648</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>00:04.427</p></td>
+<td><p>00:04.326</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 97ea4e8aec..1966027a69 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>00:44.107</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.371</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.393</p></td>
+<td><p>00:32.417</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>00:10.073</p></td>
+<td><p>00:10.130</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>00:01.635</p></td>
+<td><p>00:01.817</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 0eb5038c9b..efac09c3b5 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 0x7f1c7f30b4d0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f5aaf717560>
</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 993de5515e..9eb961bfde 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>00:07.801</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.910</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.473</p></td>
+<td><p>00:05.540</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.017</p></td>
+<td><p>00:01.044</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.577</p></td>
+<td><p>00:00.578</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>00:00.541</p></td>
+<td><p>00:00.551</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>00:00.112</p></td>
+<td><p>00:00.114</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>00:00.040</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 1f6dddb3be..1b8d7e32d6 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/tmp4kdm3pk9/input0.cc'\nsource_filename = \"/tmp/tmp4kdm3pk9/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/tmp4de87wbl/input0.cc'\nsource_filename = \"/tmp/tmp4de87wbl/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 caeb31e494..dedd8e76a3 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="494" 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="520" height="1454"><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 4ceacbf56a..d7a0e583f5 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
@@ -4,171 +4,175 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::runtime::ModuleNode Pages: 1 -->
-<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)">
+<svg width="390pt" height="1090pt"
+ viewBox="0.00 0.00 390.00 1090.00" 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 1086)">
<title>tvm::runtime::ModuleNode</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1042 365.5,-1042 365.5,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1086 386,-1086 386,4 -4,4"/>
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<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>
+<polygon fill="#bfbfbf" stroke="#000000" points="97,-424.5 97,-646.5 306,-646.5 306,-424.5 97,-424.5"/>
+<text text-anchor="middle" x="201.5" y="-634.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ModuleNode</text>
+<polyline fill="none" stroke="#000000" points="97,-627.5 306,-627.5 "/>
+<text text-anchor="start" x="105" y="-615.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="105" y="-604.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="105" y="-593.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># imports_</text>
+<polyline fill="none" stroke="#000000" points="97,-586.5 306,-586.5 "/>
+<text text-anchor="start" x="105" y="-574.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ModuleNode()</text>
+<text text-anchor="start" x="105" y="-563.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
+<text text-anchor="start" x="105" y="-552.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="105" y="-541.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
+<text text-anchor="start" x="105" y="-530.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
+<text text-anchor="start" x="105" y="-519.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetSource()</text>
+<text text-anchor="start" x="105" y="-508.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFormat()</text>
+<text text-anchor="start" x="105" y="-497.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="105" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Import()</text>
+<text text-anchor="start" x="105" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFuncFromEnv()</text>
+<text text-anchor="start" x="105" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ imports()</text>
+<text text-anchor="start" x="105" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsDSOExportable()</text>
+<text text-anchor="start" x="105" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ImplementsFunction()</text>
+<text text-anchor="start" x="105" y="-431.5" 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,-321.5 203,-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>
-<text text-anchor="start" x="8" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ late_bound_constant</text>
-<text text-anchor="start" x="8" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_names</text>
-<text text-anchor="start" x="8" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ global_map</text>
-<text text-anchor="start" x="8" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ primitive_map</text>
-<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,-184.5 203,-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>
-<text text-anchor="start" x="8" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Save()</text>
-<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">+ 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>
+<polygon fill="#ffffff" stroke="#000000" points="0,-44.5 0,-343.5 203,-343.5 203,-44.5 0,-44.5"/>
+<text text-anchor="middle" x="101.5" y="-331.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Executable</text>
+<polyline fill="none" stroke="#000000" points="0,-324.5 203,-324.5 "/>
+<text text-anchor="start" x="8" y="-312.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ virtual_devices</text>
+<text text-anchor="start" x="8" y="-301.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ host_device_index</text>
+<text text-anchor="start" x="8" y="-290.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ constants</text>
+<text text-anchor="start" x="8" y="-279.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ late_bound_constant</text>
+<text text-anchor="start" x="8" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_names</text>
+<text text-anchor="start" x="8" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ global_map</text>
+<text text-anchor="start" x="8" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ primitive_map</text>
+<text text-anchor="start" x="8" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ op_attrs</text>
+<text text-anchor="start" x="8" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ functions</text>
+<text text-anchor="start" x="8" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ const_device_indexes</text>
+<polyline fill="none" stroke="#000000" points="0,-206.5 203,-206.5 "/>
+<text text-anchor="start" x="8" y="-194.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="8" y="-183.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
+<text text-anchor="start" x="8" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
+<text text-anchor="start" x="8" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Save()</text>
+<text text-anchor="start" x="8" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsTo</text>
+<text text-anchor="start" x="8" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
+<text text-anchor="start" x="8" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MoveLateBoundConstantsToFile()</text>
+<text text-anchor="start" x="8" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetLateBoundConstants()</text>
+<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFrom</text>
+<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Stream()</text>
+<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadLateBoundConstantsFromMap()</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">and 12 more...</text>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Load()</text>
</a>
</g>
</g>
<!-- Node0->Node2 -->
<g id="edge2" class="edge">
<title>Node0->Node2</title>
-<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"/>
+<path fill="none" stroke="#191970" d="M166.0468,-414.4272C159.3435,-391.5356 152.2581,-367.339 145.333,-343.6898"/>
+<polygon fill="none" stroke="#191970" points="162.7254,-415.5393 168.8946,-424.1527 169.4433,-413.572 162.7254,-415.5393"/>
</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="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>
+<polygon fill="#ffffff" stroke="#000000" points="221,-.5 221,-387.5 382,-387.5 382,-.5 221,-.5"/>
+<text text-anchor="start" x="229" y="-375.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Virtual</text>
+<text text-anchor="middle" x="301.5" y="-364.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Machine</text>
+<polyline fill="none" stroke="#000000" points="221,-357.5 382,-357.5 "/>
+<text text-anchor="start" x="229" y="-345.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># packed_funcs_</text>
+<text text-anchor="start" x="229" y="-334.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># frames_</text>
+<text text-anchor="start" x="229" y="-323.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># func_index_</text>
+<text text-anchor="start" x="229" y="-312.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># code_</text>
+<text text-anchor="start" x="229" y="-301.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># pc_</text>
+<text text-anchor="start" x="229" y="-290.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># return_register_</text>
+<text text-anchor="start" x="229" y="-279.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># exec_</text>
+<text text-anchor="start" x="229" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># inputs_</text>
+<text text-anchor="start" x="229" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># set_outputs_enabled_</text>
+<text text-anchor="start" x="229" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># preresult_op_index_</text>
+<text text-anchor="start" x="229" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># output_tensor_reg_indices_</text>
+<text text-anchor="start" x="229" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># outputs_</text>
+<text text-anchor="start" x="229" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># devices_</text>
+<text text-anchor="start" x="229" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># allocators_</text>
+<text text-anchor="start" x="229" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># const_pool_</text>
+<polyline fill="none" stroke="#000000" points="221,-184.5 382,-184.5 "/>
+<text text-anchor="start" x="229" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="229" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~VirtualMachine()</text>
+<text text-anchor="start" x="229" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
+<text text-anchor="start" x="229" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VirtualMachine()</text>
+<text text-anchor="start" x="229" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadExecutable()</text>
+<text text-anchor="start" x="229" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PushFrame()</text>
+<text text-anchor="start" x="229" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PopFrame()</text>
+<text text-anchor="start" x="229" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># WriteRegister()</text>
+<text text-anchor="start" x="229" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ReadRegister()</text>
+<text text-anchor="start" x="229" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># LoadScalarInt()</text>
+<text text-anchor="start" x="229" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="229" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="229" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="229" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># InvokePacked()</text>
+<text text-anchor="start" x="229" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Init()</text>
+<text text-anchor="start" x="229" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</a>
</g>
</g>
<!-- Node0->Node3 -->
<g id="edge3" class="edge">
<title>Node0->Node3</title>
-<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"/>
+<path fill="none" stroke="#191970" d="M236.9607,-414.4017C239.512,-405.6892 242.1185,-396.7878 244.7505,-387.7996"/>
+<polygon fill="none" stroke="#191970" points="233.5567,-413.572 234.1054,-424.1527 240.2746,-415.5393 233.5567,-413.572"/>
</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="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>
+<polygon fill="#ffffff" stroke="#000000" points="110,-683.5 110,-1081.5 293,-1081.5 293,-683.5 110,-683.5"/>
+<text text-anchor="middle" x="201.5" y="-1069.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
+<polyline fill="none" stroke="#000000" points="110,-1062.5 293,-1062.5 "/>
+<text text-anchor="start" x="118" y="-1050.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="118" y="-1039.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
+<text text-anchor="start" x="118" y="-1028.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
+<text text-anchor="start" x="118" y="-1017.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
+<text text-anchor="start" x="118" y="-1006.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
+<text text-anchor="start" x="118" y="-995.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
+<text text-anchor="start" x="118" y="-984.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
+<text text-anchor="start" x="118" y="-973.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
+<text text-anchor="start" x="118" y="-962.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="118" y="-951.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="118" y="-940.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="118" y="-929.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="118" y="-918.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
+<text text-anchor="start" x="118" y="-907.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
+<text text-anchor="start" x="118" y="-896.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
+<polyline fill="none" stroke="#000000" points="110,-889.5 293,-889.5 "/>
+<text text-anchor="start" x="118" y="-877.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
+<text text-anchor="start" x="118" y="-866.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
+<text text-anchor="start" x="118" y="-855.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
+<text text-anchor="start" x="118" y="-844.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
+<text text-anchor="start" x="118" y="-833.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="118" y="-822.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="118" y="-811.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="118" y="-800.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="118" y="-789.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="118" y="-778.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="118" y="-767.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
+<text text-anchor="start" x="118" y="-756.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
+<text text-anchor="start" x="118" y="-745.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
+<text text-anchor="start" x="118" y="-734.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="118" y="-723.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
+<text text-anchor="start" x="118" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
+<text text-anchor="start" x="118" y="-701.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
+<text text-anchor="start" x="118" y="-690.5" 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="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"/>
+<path fill="none" stroke="#191970" d="M201.5,-673.1635C201.5,-664.1306 201.5,-655.2331 201.5,-646.575"/>
+<polygon fill="none" stroke="#191970" points="198.0001,-673.414 201.5,-683.4141 205.0001,-673.4141 198.0001,-673.414"/>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine-members.html b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine-members.html
index a1727233af..349b8ecacc 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine-members.html
@@ -107,33 +107,41 @@ $(function() {
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a7d46e436c01133647cd303719752f456">inputs_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#aa5f4724e2e702ef9d5c34e85dec53b02">Invoke</a>(const VMFunction &func, const std::vector< ObjectRef > &args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a1094291352e07e4c827a88b1167b89ad">Invoke</a>(const std::string &name, const std::vector< ObjectRef > &args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a33df7df2ae3019ae1d6bd11427acb747">InvokeGlobal</a>(const VMFunction &func, const std::vector< ObjectRef > &args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a89bc186467de25e51802e0ce739f436b">InvokePacked</a>(Index packed_index, const PackedFunc &func, Index arg_count, Index output_size, const std::vector< ObjectRef > &args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">virtua [...]
- <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_1VirtualMachine.html#a570f98cee9ed472018dea24bfcb108eb">LoadExecutable</a>(const ObjectPtr< Executable > &exec)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a27fc0a1ece314cdd8478a5f68cdd3954">LoadScalarInt</a>(RegName reg) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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#a133436a9ec5c4a768b94102bf95a660b">Object</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></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ab7968feb6ad38ecaffc320e13819d826">Object</a>(const Object &other)</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#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &&other)</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#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &other)</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#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &&other)</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_1VirtualMachine.html#a4e3d0f62ef25486968335336d1445bfa">OpStartHook</a>(Instruction instr)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">virtual</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a4f9142d370e9629f86b792c4328c24a4">OpStopHook</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ae2e5377a5dbf7335ed8989512457a2f5">packed_funcs_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a583f4afb3292882df571a4fdf3cbf947">pc_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a5a60fe06f720e26c749a80211f1ee620">PopFrame</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a05f2bc216da23c035522d5dde356a920">PushFrame</a>(Index arg_count, Index ret_pc, const VMFunction &vm_func)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a3caf2fbd01a9160d7a68982df566d2d4">ReadRegister</a>(RegName reg) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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#a0d492efee331e2239a093f4b2017c10f">ref_counter_</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">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55549a6c23987890246248682560a03d">RefCounterType</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#afd0505002da7e7f86f82b2f3325ff127">return_register_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ad83dfc94ba5e62875df9e780c750487b">RunLoop</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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#ad94d79729ac85aa7c976e23d39066383">RuntimeTypeIndex</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">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#acd613ea7faf2fc100d1e8b0fd80020c3">SaveToBinary</a>(dmlc::Stream *stream)</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#ad06785ce4a9daf8602748f1b9cff5b90">SaveToFile</a>(const std::string &file_name, 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_1vm_1_1VirtualMachine.html#a6cc5773f6bc5066ddab180a443df72a9">Invoke</a>(const VMFunction &func, const std::vector< ObjectRef > &input_args, const std::vector< ObjectRef > &output_args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a33df7df2ae3019ae1d6bd11427acb747">InvokeGlobal</a>(const VMFunction &func, const std::vector< ObjectRef > &args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a89bc186467de25e51802e0ce739f436b">InvokePacked</a>(Index packed_index, const PackedFunc &func, Index arg_count, Index output_size, const std::vector< ObjectRef > &args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span><span class="m [...]
+ <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_1VirtualMachine.html#a570f98cee9ed472018dea24bfcb108eb">LoadExecutable</a>(const ObjectPtr< Executable > &exec)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a27fc0a1ece314cdd8478a5f68cdd3954">LoadScalarInt</a>(RegName reg) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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#a133436a9ec5c4a768b94102bf95a660b">Object</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></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ab7968feb6ad38ecaffc320e13819d826">Object</a>(const Object &other)</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#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &&other)</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#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &other)</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#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &&other)</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_1VirtualMachine.html#a4e3d0f62ef25486968335336d1445bfa">OpStartHook</a>(Instruction instr)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a4f9142d370e9629f86b792c4328c24a4">OpStopHook</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">virtual</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa98e90db9a3ef70c732b5322171023c2">output_tensor_reg_indices_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a43d9a2e6056305a8c14941eb08f2cf29">outputs_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#ae2e5377a5dbf7335ed8989512457a2f5">packed_funcs_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a583f4afb3292882df571a4fdf3cbf947">pc_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a5a60fe06f720e26c749a80211f1ee620">PopFrame</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a37b4a705186bf76cb9aa5168dcbc3651">preresult_op_index_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#ac2ca0dc6162002d400e56ccc4c41fb9c">PrintInfoAndSetInputArgs</a>(const VMFunction &func, const std::vector< ObjectRef > &args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a05f2bc216da23c035522d5dde356a920">PushFrame</a>(Index arg_count, Index ret_pc, const VMFunction &vm_func)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a3caf2fbd01a9160d7a68982df566d2d4">ReadRegister</a>(RegName reg) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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#a0d492efee331e2239a093f4b2017c10f">ref_counter_</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">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55549a6c23987890246248682560a03d">RefCounterType</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#afd0505002da7e7f86f82b2f3325ff127">return_register_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a08164ef76393a4efb002c1ea6b8ae447">RunLoop</a>(const std::vector< Index > &output_tensor_reg_indices={})</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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#ad94d79729ac85aa7c976e23d39066383">RuntimeTypeIndex</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">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#acd613ea7faf2fc100d1e8b0fd80020c3">SaveToBinary</a>(dmlc::Stream *stream)</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#ad06785ce4a9daf8602748f1b9cff5b90">SaveToFile</a>(const std::string &file_name, 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_1vm_1_1VirtualMachine.html#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9">set_outputs_enabled_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a0594113c83505e3368a7f99394a14595">SetInput</a>(std::string name, TVMArgs args, int offset)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#ab66c1484cfb630914dd41da36ab91db1">SetOneInput</a>(std::string name, const TVMArgValue &tag, const TVMArgValue &tensor)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a2ee3a67f145ed44cabfb4d456c048445">SetOutputs</a>(std::string name, TVMArgs args)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</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_1vm_1_1VirtualMachine.html#a95a0552177a93f4839ab431756efeaf3">SetOutputTensorsToRegister</a>(const std::string &func_name, const std::vector< ObjectRef > &outputs)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html">tvm::runtime::vm::VirtualMachine</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#ac44750d06e11a275b10072b982ef4b13">TVM_DECLARE_FINAL_OBJECT_INFO</a>(ModuleNode, Object)</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_1Object.html#a481f01923b14e1851ebd38506e9c66ea">type_index</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#a4bfc2586cb55f2af47728187b3256255">type_index_</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">protected</span></td></tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html
index 59440974dd..d3facf9466 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html
@@ -79,13 +79,13 @@ $(function() {
<div class="dynheader">
Inheritance diagram for tvm::runtime::vm::VirtualMachine:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1runtime_1_1vm_1_1VirtualMachine__inherit__graph.svg" width="290" 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_1vm_1_1VirtualMachine__inherit__graph.svg" width="290" height="1454"><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">
Collaboration diagram for tvm::runtime::vm::VirtualMachine:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1runtime_1_1vm_1_1VirtualMachine__coll__graph.svg" width="1002" height="1498"><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_1vm_1_1VirtualMachine__coll__graph.svg" width="1002" height="1556"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<table class="memberdecls">
@@ -184,15 +184,18 @@ Protected Member Functions</h2></td></tr>
<tr class="memitem:a1094291352e07e4c827a88b1167b89ad"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a1094291352e07e4c827a88b1167b89ad">Invoke</a> (const std::string &name, const std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > &args)</td></tr>
<tr class="memdesc:a1094291352e07e4c827a88b1167b89ad"><td class="mdescLeft"> </td><td class="mdescRight">Invoke a VM function by name. <a href="#a1094291352e07e4c827a88b1167b89ad">More...</a><br /></td></tr>
<tr class="separator:a1094291352e07e4c827a88b1167b89ad"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a6cc5773f6bc5066ddab180a443df72a9"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6cc5773f6bc5066ddab180a443df72a9">Invoke</a> (const <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html">VMFunction</a> &func, const std::vector< <a class="el" href="classt [...]
+<tr class="memdesc:a6cc5773f6bc5066ddab180a443df72a9"><td class="mdescLeft"> </td><td class="mdescRight">Invoke a VM function. <a href="#a6cc5773f6bc5066ddab180a443df72a9">More...</a><br /></td></tr>
+<tr class="separator:a6cc5773f6bc5066ddab180a443df72a9"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a89bc186467de25e51802e0ce739f436b"><td class="memItemLeft" align="right" valign="top">virtual void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a89bc186467de25e51802e0ce739f436b">InvokePacked</a> (<a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">Index</a> packed_index, const <a class="el" href="classtvm_1_1runtime_1_1PackedFunc.html">PackedFunc</a> &f [...]
<tr class="memdesc:a89bc186467de25e51802e0ce739f436b"><td class="mdescLeft"> </td><td class="mdescRight">Invoke a PackedFunction. <a href="#a89bc186467de25e51802e0ce739f436b">More...</a><br /></td></tr>
<tr class="separator:a89bc186467de25e51802e0ce739f436b"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a29c724a8ff2f88d8f4b5ba72e873b9c3"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a29c724a8ff2f88d8f4b5ba72e873b9c3">Init</a> (const std::vector< <a class="el" href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">Device</a> > &physical_devices, const std::vector< <a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a71f7e [...]
<tr class="memdesc:a29c724a8ff2f88d8f4b5ba72e873b9c3"><td class="mdescLeft"> </td><td class="mdescRight">Initialize the virtual machine for a set of (physical) devices. <a href="#a29c724a8ff2f88d8f4b5ba72e873b9c3">More...</a><br /></td></tr>
<tr class="separator:a29c724a8ff2f88d8f4b5ba72e873b9c3"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:ad83dfc94ba5e62875df9e780c750487b"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ad83dfc94ba5e62875df9e780c750487b">RunLoop</a> ()</td></tr>
-<tr class="memdesc:ad83dfc94ba5e62875df9e780c750487b"><td class="mdescLeft"> </td><td class="mdescRight">Run VM dispatch loop. <a href="#ad83dfc94ba5e62875df9e780c750487b">More...</a><br /></td></tr>
-<tr class="separator:ad83dfc94ba5e62875df9e780c750487b"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a08164ef76393a4efb002c1ea6b8ae447"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a08164ef76393a4efb002c1ea6b8ae447">RunLoop</a> (const std::vector< <a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">Index</a> > &output_tensor_reg_indices={})</td></tr>
+<tr class="memdesc:a08164ef76393a4efb002c1ea6b8ae447"><td class="mdescLeft"> </td><td class="mdescRight">Run VM dispatch loop. <a href="#a08164ef76393a4efb002c1ea6b8ae447">More...</a><br /></td></tr>
+<tr class="separator:a08164ef76393a4efb002c1ea6b8ae447"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a6474e850ca2858befcecee22fe8689a1"><td class="memItemLeft" align="right" valign="top"><a class="el" href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">Device</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6474e850ca2858befcecee22fe8689a1">GetDevice</a> (<a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">Index</a> device_index) const</td></tr>
<tr class="memdesc:a6474e850ca2858befcecee22fe8689a1"><td class="mdescLeft"> </td><td class="mdescRight">Get device from the device list based on a given device index. <a href="#a6474e850ca2858befcecee22fe8689a1">More...</a><br /></td></tr>
<tr class="separator:a6474e850ca2858befcecee22fe8689a1"><td class="memSeparator" colspan="2"> </td></tr>
@@ -207,6 +210,15 @@ Protected Member Functions</h2></td></tr>
<tr class="memitem:ab66c1484cfb630914dd41da36ab91db1"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ab66c1484cfb630914dd41da36ab91db1">SetOneInput</a> (std::string name, const <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html">TVMArgValue</a> &tag, const <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html">TVMArgValue</a> &tensor)</td></tr>
<tr class="memdesc:ab66c1484cfb630914dd41da36ab91db1"><td class="mdescLeft"> </td><td class="mdescRight">Set one input tensor with index or name to a function. <a href="#ab66c1484cfb630914dd41da36ab91db1">More...</a><br /></td></tr>
<tr class="separator:ab66c1484cfb630914dd41da36ab91db1"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a2ee3a67f145ed44cabfb4d456c048445"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a2ee3a67f145ed44cabfb4d456c048445">SetOutputs</a> (std::string name, <a class="el" href="classtvm_1_1runtime_1_1TVMArgs.html">TVMArgs</a> args)</td></tr>
+<tr class="memdesc:a2ee3a67f145ed44cabfb4d456c048445"><td class="mdescLeft"> </td><td class="mdescRight">Set pre-allocated output tensors to a function. It is native implementation of 'set_outputs' python method. It is used in scenario when output tensors are allocated outside each invocation. Note: it sets set_outputs_enabled_[name] true and fill outputs_[name] but after invocation the first is switched off and the second is cleared. <a href="#a2ee3a67f145ed44cabfb4d456c048445">Mo [...]
+<tr class="separator:a2ee3a67f145ed44cabfb4d456c048445"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ac2ca0dc6162002d400e56ccc4c41fb9c"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ac2ca0dc6162002d400e56ccc4c41fb9c">PrintInfoAndSetInputArgs</a> (const <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html">VMFunction</a> &func, const std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > [...]
+<tr class="memdesc:ac2ca0dc6162002d400e56ccc4c41fb9c"><td class="mdescLeft"> </td><td class="mdescRight">Preparation part of Invoke method before RunLoop. <a href="#ac2ca0dc6162002d400e56ccc4c41fb9c">More...</a><br /></td></tr>
+<tr class="separator:ac2ca0dc6162002d400e56ccc4c41fb9c"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a95a0552177a93f4839ab431756efeaf3"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a95a0552177a93f4839ab431756efeaf3">SetOutputTensorsToRegister</a> (const std::string &func_name, const std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > &outputs)</td></tr>
+<tr class="memdesc:a95a0552177a93f4839ab431756efeaf3"><td class="mdescLeft"> </td><td class="mdescRight">Set pre-allocated outputs to register for specified function. <a href="#a95a0552177a93f4839ab431756efeaf3">More...</a><br /></td></tr>
+<tr class="separator:a95a0552177a93f4839ab431756efeaf3"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a4e3d0f62ef25486968335336d1445bfa"><td class="memItemLeft" align="right" valign="top">virtual void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a4e3d0f62ef25486968335336d1445bfa">OpStartHook</a> (<a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html">Instruction</a> instr)</td></tr>
<tr class="memdesc:a4e3d0f62ef25486968335336d1445bfa"><td class="mdescLeft"> </td><td class="mdescRight">Internal hook for profiling the start of an op. <a href="#a4e3d0f62ef25486968335336d1445bfa">More...</a><br /></td></tr>
<tr class="separator:a4e3d0f62ef25486968335336d1445bfa"><td class="memSeparator" colspan="2"> </td></tr>
@@ -247,6 +259,18 @@ Protected Attributes</h2></td></tr>
<tr class="memitem:a7d46e436c01133647cd303719752f456"><td class="memItemLeft" align="right" valign="top">std::unordered_map< std::string, std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a7d46e436c01133647cd303719752f456">inputs_</a></td></tr>
<tr class="memdesc:a7d46e436c01133647cd303719752f456"><td class="mdescLeft"> </td><td class="mdescRight">The function name to inputs mapping. <a href="#a7d46e436c01133647cd303719752f456">More...</a><br /></td></tr>
<tr class="separator:a7d46e436c01133647cd303719752f456"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a6a3eb3eb9362ee6567e9ee6a6bc7ccf9"><td class="memItemLeft" align="right" valign="top">std::unordered_map< std::string, bool > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9">set_outputs_enabled_</a></td></tr>
+<tr class="memdesc:a6a3eb3eb9362ee6567e9ee6a6bc7ccf9"><td class="mdescLeft"> </td><td class="mdescRight">The function name to flag enabling scenario with set outputs. <a href="#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9">More...</a><br /></td></tr>
+<tr class="separator:a6a3eb3eb9362ee6567e9ee6a6bc7ccf9"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a37b4a705186bf76cb9aa5168dcbc3651"><td class="memItemLeft" align="right" valign="top"><a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">Index</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a37b4a705186bf76cb9aa5168dcbc3651">preresult_op_index_</a> = -1</td></tr>
+<tr class="memdesc:a37b4a705186bf76cb9aa5168dcbc3651"><td class="mdescLeft"> </td><td class="mdescRight">The index of operation which destination is result. <a href="#a37b4a705186bf76cb9aa5168dcbc3651">More...</a><br /></td></tr>
+<tr class="separator:a37b4a705186bf76cb9aa5168dcbc3651"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aa98e90db9a3ef70c732b5322171023c2"><td class="memItemLeft" align="right" valign="top">std::unordered_map< std::string, std::vector< <a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">Index</a> > > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa98e90db9a3ef70c732b5322171023c2">output_tensor_reg_indices_</a></td></tr>
+<tr class="memdesc:aa98e90db9a3ef70c732b5322171023c2"><td class="mdescLeft"> </td><td class="mdescRight">The function name to indices of output tensors in register file. <a href="#aa98e90db9a3ef70c732b5322171023c2">More...</a><br /></td></tr>
+<tr class="separator:aa98e90db9a3ef70c732b5322171023c2"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a43d9a2e6056305a8c14941eb08f2cf29"><td class="memItemLeft" align="right" valign="top">std::unordered_map< std::string, std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a43d9a2e6056305a8c14941eb08f2cf29">outputs_</a></td></tr>
+<tr class="memdesc:a43d9a2e6056305a8c14941eb08f2cf29"><td class="mdescLeft"> </td><td class="mdescRight">The function name to pre-allocated outputs mapping. <a href="#a43d9a2e6056305a8c14941eb08f2cf29">More...</a><br /></td></tr>
+<tr class="separator:a43d9a2e6056305a8c14941eb08f2cf29"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a602daa8d70ae598a833d8601d1ef6d95"><td class="memItemLeft" align="right" valign="top">std::vector< <a class="el" href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">Device</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a602daa8d70ae598a833d8601d1ef6d95">devices_</a></td></tr>
<tr class="memdesc:a602daa8d70ae598a833d8601d1ef6d95"><td class="mdescLeft"> </td><td class="mdescRight">The "physical" devices the VM can execute primitives on. All "device indexes" are w.r.t. this vector. Each entry in this vector must match the corresponding entry in the executable's "virtual" devices vector. <a href="#a602daa8d70ae598a833d8601d1ef6d95">More...</a><br /></td></tr>
<tr class="separator:a602daa8d70ae598a833d8601d1ef6d95"><td class="memSeparator" colspan="2"> </td></tr>
@@ -526,7 +550,7 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
<a id="aa5f4724e2e702ef9d5c34e85dec53b02"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#aa5f4724e2e702ef9d5c34e85dec53b02">◆ </a></span>Invoke() <span class="overload">[1/2]</span></h2>
+<h2 class="memtitle"><span class="permalink"><a href="#aa5f4724e2e702ef9d5c34e85dec53b02">◆ </a></span>Invoke() <span class="overload">[1/3]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -572,7 +596,7 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
<a id="a1094291352e07e4c827a88b1167b89ad"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a1094291352e07e4c827a88b1167b89ad">◆ </a></span>Invoke() <span class="overload">[2/2]</span></h2>
+<h2 class="memtitle"><span class="permalink"><a href="#a1094291352e07e4c827a88b1167b89ad">◆ </a></span>Invoke() <span class="overload">[2/3]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -615,6 +639,59 @@ Additional Inherited Members</h2></td></tr>
</dl>
<dl class="section return"><dt>Returns</dt><dd>The object representing the result. </dd></dl>
+</div>
+</div>
+<a id="a6cc5773f6bc5066ddab180a443df72a9"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a6cc5773f6bc5066ddab180a443df72a9">◆ </a></span>Invoke() <span class="overload">[3/3]</span></h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> tvm::runtime::vm::VirtualMachine::Invoke </td>
+ <td>(</td>
+ <td class="paramtype">const <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html">VMFunction</a> & </td>
+ <td class="paramname"><em>func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">const std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > & </td>
+ <td class="paramname"><em>input_args</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">const std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > & </td>
+ <td class="paramname"><em>output_args</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">protected</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>Invoke a VM function. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">func</td><td>The function. </td></tr>
+ <tr><td class="paramname">input_args</td><td>The input arguments to the function. </td></tr>
+ <tr><td class="paramname">output_args</td><td>The pre-allocated output arguments of the function. </td></tr>
+ </table>
+ </dd>
+</dl>
+<dl class="section return"><dt>Returns</dt><dd>The object(s) representing the result. </dd></dl>
+
</div>
</div>
<a id="a33df7df2ae3019ae1d6bd11427acb747"></a>
@@ -880,6 +957,51 @@ Additional Inherited Members</h2></td></tr>
<p>Pop a frame off the call stack. </p>
<dl class="section return"><dt>Returns</dt><dd>The number of frames left. </dd></dl>
+</div>
+</div>
+<a id="ac2ca0dc6162002d400e56ccc4c41fb9c"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#ac2ca0dc6162002d400e56ccc4c41fb9c">◆ </a></span>PrintInfoAndSetInputArgs()</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">void tvm::runtime::vm::VirtualMachine::PrintInfoAndSetInputArgs </td>
+ <td>(</td>
+ <td class="paramtype">const <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html">VMFunction</a> & </td>
+ <td class="paramname"><em>func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">const std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > & </td>
+ <td class="paramname"><em>args</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">protected</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>Preparation part of Invoke method before RunLoop. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">func</td><td>the function. </td></tr>
+ <tr><td class="paramname">args</td><td>input args </td></tr>
+ </table>
+ </dd>
+</dl>
+
</div>
</div>
<a id="a05f2bc216da23c035522d5dde356a920"></a>
@@ -961,8 +1083,8 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
-<a id="ad83dfc94ba5e62875df9e780c750487b"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#ad83dfc94ba5e62875df9e780c750487b">◆ </a></span>RunLoop()</h2>
+<a id="a08164ef76393a4efb002c1ea6b8ae447"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a08164ef76393a4efb002c1ea6b8ae447">◆ </a></span>RunLoop()</h2>
<div class="memitem">
<div class="memproto">
@@ -973,7 +1095,8 @@ Additional Inherited Members</h2></td></tr>
<tr>
<td class="memname">void tvm::runtime::vm::VirtualMachine::RunLoop </td>
<td>(</td>
- <td class="paramname"></td><td>)</td>
+ <td class="paramtype">const std::vector< <a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">Index</a> > & </td>
+ <td class="paramname"><em>output_tensor_reg_indices</em> = <code>{}</code></td><td>)</td>
<td></td>
</tr>
</table>
@@ -1090,6 +1213,96 @@ Additional Inherited Members</h2></td></tr>
</dd>
</dl>
+</div>
+</div>
+<a id="a2ee3a67f145ed44cabfb4d456c048445"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a2ee3a67f145ed44cabfb4d456c048445">◆ </a></span>SetOutputs()</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">void tvm::runtime::vm::VirtualMachine::SetOutputs </td>
+ <td>(</td>
+ <td class="paramtype">std::string </td>
+ <td class="paramname"><em>name</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1TVMArgs.html">TVMArgs</a> </td>
+ <td class="paramname"><em>args</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">protected</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>Set pre-allocated output tensors to a function. It is native implementation of 'set_outputs' python method. It is used in scenario when output tensors are allocated outside each invocation. Note: it sets set_outputs_enabled_[name] true and fill outputs_[name] but after invocation the first is switched off and the second is cleared. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">name</td><td>The function name </td></tr>
+ <tr><td class="paramname">args</td><td>outputs to the function. </td></tr>
+ </table>
+ </dd>
+</dl>
+
+</div>
+</div>
+<a id="a95a0552177a93f4839ab431756efeaf3"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a95a0552177a93f4839ab431756efeaf3">◆ </a></span>SetOutputTensorsToRegister()</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">void tvm::runtime::vm::VirtualMachine::SetOutputTensorsToRegister </td>
+ <td>(</td>
+ <td class="paramtype">const std::string & </td>
+ <td class="paramname"><em>func_name</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">const std::vector< <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> > & </td>
+ <td class="paramname"><em>outputs</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">protected</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>Set pre-allocated outputs to register for specified function. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">func_name</td><td>The function's name. </td></tr>
+ <tr><td class="paramname">outputs</td><td>set of output tensors. </td></tr>
+ </table>
+ </dd>
+</dl>
+
</div>
</div>
<a id="a00f035566a720dbac56f5dea042fb0ec"></a>
@@ -1357,6 +1570,54 @@ Additional Inherited Members</h2></td></tr>
<p>The function name to inputs mapping. </p>
+</div>
+</div>
+<a id="aa98e90db9a3ef70c732b5322171023c2"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#aa98e90db9a3ef70c732b5322171023c2">◆ </a></span>output_tensor_reg_indices_</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">std::unordered_map<std::string, std::vector<<a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">Index</a>> > tvm::runtime::vm::VirtualMachine::output_tensor_reg_indices_</td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">protected</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>The function name to indices of output tensors in register file. </p>
+
+</div>
+</div>
+<a id="a43d9a2e6056305a8c14941eb08f2cf29"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a43d9a2e6056305a8c14941eb08f2cf29">◆ </a></span>outputs_</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">std::unordered_map<std::string, std::vector<<a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a>> > tvm::runtime::vm::VirtualMachine::outputs_</td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">protected</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>The function name to pre-allocated outputs mapping. </p>
+
</div>
</div>
<a id="ae2e5377a5dbf7335ed8989512457a2f5"></a>
@@ -1405,6 +1666,30 @@ Additional Inherited Members</h2></td></tr>
<p>The virtual machine PC. </p>
+</div>
+</div>
+<a id="a37b4a705186bf76cb9aa5168dcbc3651"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a37b4a705186bf76cb9aa5168dcbc3651">◆ </a></span>preresult_op_index_</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname"><a class="el" href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">Index</a> tvm::runtime::vm::VirtualMachine::preresult_op_index_ = -1</td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">protected</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>The index of operation which destination is result. </p>
+
</div>
</div>
<a id="afd0505002da7e7f86f82b2f3325ff127"></a>
@@ -1429,6 +1714,30 @@ Additional Inherited Members</h2></td></tr>
<p>The special return register. </p>
+</div>
+</div>
+<a id="a6a3eb3eb9362ee6567e9ee6a6bc7ccf9"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9">◆ </a></span>set_outputs_enabled_</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">std::unordered_map<std::string, bool> tvm::runtime::vm::VirtualMachine::set_outputs_enabled_</td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">protected</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>The function name to flag enabling scenario with set outputs. </p>
+
</div>
</div>
<hr/>The documentation for this class was generated from the following file:<ul>
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine__coll__graph.svg
index bf0db5bad5..c476eca904 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine__coll__graph.svg
@@ -4,274 +4,278 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::runtime::vm::VirtualMachine Pages: 1 -->
-<svg width="751pt" height="1123pt"
- viewBox="0.00 0.00 750.50 1123.00" 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 1119)">
+<svg width="751pt" height="1167pt"
+ viewBox="0.00 0.00 750.50 1167.00" 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 1163)">
<title>tvm::runtime::vm::VirtualMachine</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1119 746.5,-1119 746.5,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1163 746.5,-1163 746.5,4 -4,4"/>
<!-- Node3 -->
<g id="node1" class="node">
<title>Node3</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="309.5,-.5 309.5,-310.5 449.5,-310.5 449.5,-.5 309.5,-.5"/>
-<text text-anchor="start" x="317.5" y="-298.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Virtual</text>
-<text text-anchor="middle" x="379.5" y="-287.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Machine</text>
-<polyline fill="none" stroke="#000000" points="309.5,-280.5 449.5,-280.5 "/>
-<text text-anchor="start" x="317.5" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># packed_funcs_</text>
-<text text-anchor="start" x="317.5" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># frames_</text>
-<text text-anchor="start" x="317.5" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># func_index_</text>
-<text text-anchor="start" x="317.5" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># pc_</text>
-<text text-anchor="start" x="317.5" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># inputs_</text>
-<text text-anchor="start" x="317.5" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># devices_</text>
-<text text-anchor="start" x="317.5" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># allocators_</text>
-<text text-anchor="start" x="317.5" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># const_pool_</text>
-<polyline fill="none" stroke="#000000" points="309.5,-184.5 449.5,-184.5 "/>
-<text text-anchor="start" x="317.5" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="317.5" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~VirtualMachine()</text>
-<text text-anchor="start" x="317.5" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
-<text text-anchor="start" x="317.5" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VirtualMachine()</text>
-<text text-anchor="start" x="317.5" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadExecutable()</text>
-<text text-anchor="start" x="317.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PushFrame()</text>
-<text text-anchor="start" x="317.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PopFrame()</text>
-<text text-anchor="start" x="317.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># WriteRegister()</text>
-<text text-anchor="start" x="317.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ReadRegister()</text>
-<text text-anchor="start" x="317.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># LoadScalarInt()</text>
-<text text-anchor="start" x="317.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
-<text text-anchor="start" x="317.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
-<text text-anchor="start" x="317.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># InvokePacked()</text>
-<text text-anchor="start" x="317.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Init()</text>
-<text text-anchor="start" x="317.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># RunLoop()</text>
-<text text-anchor="start" x="317.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 7 more...</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="299,-.5 299,-354.5 460,-354.5 460,-.5 299,-.5"/>
+<text text-anchor="start" x="307" y="-342.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Virtual</text>
+<text text-anchor="middle" x="379.5" y="-331.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Machine</text>
+<polyline fill="none" stroke="#000000" points="299,-324.5 460,-324.5 "/>
+<text text-anchor="start" x="307" y="-312.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># packed_funcs_</text>
+<text text-anchor="start" x="307" y="-301.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># frames_</text>
+<text text-anchor="start" x="307" y="-290.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># func_index_</text>
+<text text-anchor="start" x="307" y="-279.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># pc_</text>
+<text text-anchor="start" x="307" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># inputs_</text>
+<text text-anchor="start" x="307" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># set_outputs_enabled_</text>
+<text text-anchor="start" x="307" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># preresult_op_index_</text>
+<text text-anchor="start" x="307" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># output_tensor_reg_indices_</text>
+<text text-anchor="start" x="307" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># outputs_</text>
+<text text-anchor="start" x="307" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># devices_</text>
+<text text-anchor="start" x="307" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># allocators_</text>
+<text text-anchor="start" x="307" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># const_pool_</text>
+<polyline fill="none" stroke="#000000" points="299,-184.5 460,-184.5 "/>
+<text text-anchor="start" x="307" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="307" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~VirtualMachine()</text>
+<text text-anchor="start" x="307" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
+<text text-anchor="start" x="307" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VirtualMachine()</text>
+<text text-anchor="start" x="307" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadExecutable()</text>
+<text text-anchor="start" x="307" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PushFrame()</text>
+<text text-anchor="start" x="307" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PopFrame()</text>
+<text text-anchor="start" x="307" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># WriteRegister()</text>
+<text text-anchor="start" x="307" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ReadRegister()</text>
+<text text-anchor="start" x="307" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># LoadScalarInt()</text>
+<text text-anchor="start" x="307" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="307" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="307" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="307" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># InvokePacked()</text>
+<text text-anchor="start" x="307" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Init()</text>
+<text text-anchor="start" x="307" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</g>
<!-- Node4 -->
<g id="node2" class="node">
<title>Node4</title>
<g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1ModuleNode.html" target="_top" xlink:title="Base container of module. ">
-<polygon fill="#ffffff" stroke="#000000" points="0,-408 0,-630 209,-630 209,-408 0,-408"/>
-<text text-anchor="middle" x="104.5" y="-618" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ModuleNode</text>
-<polyline fill="none" stroke="#000000" points="0,-611 209,-611 "/>
-<text text-anchor="start" x="8" y="-599" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="8" y="-588" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="8" y="-577" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># imports_</text>
-<polyline fill="none" stroke="#000000" points="0,-570 209,-570 "/>
-<text text-anchor="start" x="8" y="-558" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ModuleNode()</text>
-<text text-anchor="start" x="8" y="-547" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
-<text text-anchor="start" x="8" y="-536" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="8" y="-525" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
-<text text-anchor="start" x="8" y="-514" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
-<text text-anchor="start" x="8" y="-503" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetSource()</text>
-<text text-anchor="start" x="8" y="-492" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFormat()</text>
-<text text-anchor="start" x="8" y="-481" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="8" y="-470" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Import()</text>
-<text text-anchor="start" x="8" y="-459" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFuncFromEnv()</text>
-<text text-anchor="start" x="8" y="-448" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ imports()</text>
-<text text-anchor="start" x="8" y="-437" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsDSOExportable()</text>
-<text text-anchor="start" x="8" y="-426" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ImplementsFunction()</text>
-<text text-anchor="start" x="8" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
+<polygon fill="#ffffff" stroke="#000000" points="0,-452 0,-674 209,-674 209,-452 0,-452"/>
+<text text-anchor="middle" x="104.5" y="-662" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ModuleNode</text>
+<polyline fill="none" stroke="#000000" points="0,-655 209,-655 "/>
+<text text-anchor="start" x="8" y="-643" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="8" y="-632" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="8" y="-621" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># imports_</text>
+<polyline fill="none" stroke="#000000" points="0,-614 209,-614 "/>
+<text text-anchor="start" x="8" y="-602" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ModuleNode()</text>
+<text text-anchor="start" x="8" y="-591" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
+<text text-anchor="start" x="8" y="-580" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="8" y="-569" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
+<text text-anchor="start" x="8" y="-558" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
+<text text-anchor="start" x="8" y="-547" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetSource()</text>
+<text text-anchor="start" x="8" y="-536" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFormat()</text>
+<text text-anchor="start" x="8" y="-525" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="8" y="-514" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Import()</text>
+<text text-anchor="start" x="8" y="-503" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFuncFromEnv()</text>
+<text text-anchor="start" x="8" y="-492" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ imports()</text>
+<text text-anchor="start" x="8" y="-481" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsDSOExportable()</text>
+<text text-anchor="start" x="8" y="-470" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ImplementsFunction()</text>
+<text text-anchor="start" x="8" y="-459" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
</a>
</g>
</g>
<!-- Node4->Node3 -->
<g id="edge1" class="edge">
<title>Node4->Node3</title>
-<path fill="none" stroke="#191970" d="M187.0368,-399.6126C197.1682,-385.4926 207.4821,-371.3611 217.5,-358 246.8037,-318.9167 280.3681,-276.5875 309.3176,-240.7843"/>
-<polygon fill="none" stroke="#191970" points="184.0666,-397.749 181.0963,-407.919 189.7604,-401.821 184.0666,-397.749"/>
+<path fill="none" stroke="#191970" d="M188.2079,-443.3643C198.0553,-429.4003 207.9825,-415.3732 217.5,-402 243.8363,-364.9946 272.8038,-324.7182 298.8714,-288.6282"/>
+<polygon fill="none" stroke="#191970" points="185.3223,-441.3831 182.4227,-451.5734 191.0442,-445.4155 185.3223,-441.3831"/>
</g>
<!-- Node5 -->
<g id="node3" class="node">
<title>Node5</title>
<g id="a_node3"><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="13,-727.5 13,-1114.5 196,-1114.5 196,-727.5 13,-727.5"/>
-<text text-anchor="middle" x="104.5" y="-1102.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
-<polyline fill="none" stroke="#000000" points="13,-1095.5 196,-1095.5 "/>
-<text text-anchor="start" x="21" y="-1083.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="21" y="-1072.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
-<text text-anchor="start" x="21" y="-1061.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
-<text text-anchor="start" x="21" y="-1050.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
-<text text-anchor="start" x="21" y="-1039.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
-<text text-anchor="start" x="21" y="-1028.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
-<text text-anchor="start" x="21" y="-1017.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
-<text text-anchor="start" x="21" y="-1006.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="21" y="-995.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="21" y="-984.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
-<text text-anchor="start" x="21" y="-973.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="21" y="-962.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="21" y="-951.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
-<text text-anchor="start" x="21" y="-940.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
-<polyline fill="none" stroke="#000000" points="13,-933.5 196,-933.5 "/>
-<text text-anchor="start" x="21" y="-921.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
-<text text-anchor="start" x="21" y="-910.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
-<text text-anchor="start" x="21" y="-899.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
-<text text-anchor="start" x="21" y="-888.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
-<text text-anchor="start" x="21" y="-877.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="21" y="-866.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-855.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-844.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-833.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="21" y="-822.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="21" y="-811.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
-<text text-anchor="start" x="21" y="-800.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
-<text text-anchor="start" x="21" y="-789.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
-<text text-anchor="start" x="21" y="-778.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
-<text text-anchor="start" x="21" y="-767.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
-<text text-anchor="start" x="21" y="-756.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
-<text text-anchor="start" x="21" y="-745.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
-<text text-anchor="start" x="21" y="-734.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
+<polygon fill="#ffffff" stroke="#000000" points="13,-771.5 13,-1158.5 196,-1158.5 196,-771.5 13,-771.5"/>
+<text text-anchor="middle" x="104.5" y="-1146.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
+<polyline fill="none" stroke="#000000" points="13,-1139.5 196,-1139.5 "/>
+<text text-anchor="start" x="21" y="-1127.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="21" y="-1116.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
+<text text-anchor="start" x="21" y="-1105.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
+<text text-anchor="start" x="21" y="-1094.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
+<text text-anchor="start" x="21" y="-1083.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
+<text text-anchor="start" x="21" y="-1072.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
+<text text-anchor="start" x="21" y="-1061.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
+<text text-anchor="start" x="21" y="-1050.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
+<text text-anchor="start" x="21" y="-1039.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="21" y="-1028.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="21" y="-1017.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="21" y="-1006.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="21" y="-995.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
+<text text-anchor="start" x="21" y="-984.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
+<polyline fill="none" stroke="#000000" points="13,-977.5 196,-977.5 "/>
+<text text-anchor="start" x="21" y="-965.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
+<text text-anchor="start" x="21" y="-954.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
+<text text-anchor="start" x="21" y="-943.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
+<text text-anchor="start" x="21" y="-932.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
+<text text-anchor="start" x="21" y="-921.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="21" y="-910.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-899.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-888.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-877.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="21" y="-866.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="21" y="-855.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
+<text text-anchor="start" x="21" y="-844.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
+<text text-anchor="start" x="21" y="-833.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
+<text text-anchor="start" x="21" y="-822.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="21" y="-811.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
+<text text-anchor="start" x="21" y="-800.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
+<text text-anchor="start" x="21" y="-789.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
+<text text-anchor="start" x="21" y="-778.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
</a>
</g>
</g>
<!-- Node5->Node4 -->
<g id="edge2" class="edge">
<title>Node5->Node4</title>
-<path fill="none" stroke="#191970" d="M104.5,-717.1906C104.5,-687.2038 104.5,-657.3004 104.5,-630.1508"/>
-<polygon fill="none" stroke="#191970" points="101.0001,-717.3593 104.5,-727.3594 108.0001,-717.3594 101.0001,-717.3593"/>
+<path fill="none" stroke="#191970" d="M104.5,-761.1906C104.5,-731.2038 104.5,-701.3004 104.5,-674.1508"/>
+<polygon fill="none" stroke="#191970" points="101.0001,-761.3593 104.5,-771.3594 108.0001,-761.3594 101.0001,-761.3593"/>
</g>
<!-- Node5->Node5 -->
<g id="edge3" class="edge">
<title>Node5->Node5</title>
-<path fill="none" stroke="#404040" d="M196.3625,-955.5649C207.0482,-949.1857 214,-937.6641 214,-921 214,-909.8038 210.8618,-900.929 205.5615,-894.3756"/>
-<polygon fill="none" stroke="#404040" points="205.4464,-894.2763 198.2907,-893.3836 196.3625,-886.4351 203.5182,-887.3277 205.4464,-894.2763"/>
-<text text-anchor="middle" x="240" y="-918.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #deleter_</text>
+<path fill="none" stroke="#404040" d="M196.3625,-999.5649C207.0482,-993.1857 214,-981.6641 214,-965 214,-953.8038 210.8618,-944.929 205.5615,-938.3756"/>
+<polygon fill="none" stroke="#404040" points="205.4464,-938.2763 198.2907,-937.3836 196.3625,-930.4351 203.5182,-931.3277 205.4464,-938.2763"/>
+<text text-anchor="middle" x="240" y="-962.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #deleter_</text>
</g>
<!-- Node6 -->
<g id="node4" class="node">
<title>Node6</title>
<g id="a_node4"><a xlink:href="classtvm_1_1runtime_1_1ObjectPtr.html" target="_top" xlink:title="{tvm::runtime::ObjectPtr\l\< tvm::runtime::vm::Executable \>\n||+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ~ObjectPtr()\l+ swap()\l+ get()\l+ operator-\>()\land 11 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="227,-430 227,-608 412,-608 412,-430 227,-430"/>
-<text text-anchor="start" x="235" y="-596" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
-<text text-anchor="middle" x="319.5" y="-585" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::vm::Executable ></text>
-<polyline fill="none" stroke="#000000" points="227,-578 412,-578 "/>
-<text text-anchor="middle" x="319.5" y="-566" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="227,-559 412,-559 "/>
+<polygon fill="#ffffff" stroke="#000000" points="227,-474 227,-652 412,-652 412,-474 227,-474"/>
+<text text-anchor="start" x="235" y="-640" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
+<text text-anchor="middle" x="319.5" y="-629" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::vm::Executable ></text>
+<polyline fill="none" stroke="#000000" points="227,-622 412,-622 "/>
+<text text-anchor="middle" x="319.5" y="-610" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="227,-603 412,-603 "/>
+<text text-anchor="start" x="235" y="-591" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="235" y="-580" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="235" y="-569" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="235" y="-558" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="235" y="-547" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="235" y="-536" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="235" y="-525" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="235" y="-514" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="235" y="-503" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="235" y="-492" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="235" y="-481" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
-<text text-anchor="start" x="235" y="-470" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
-<text text-anchor="start" x="235" y="-459" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="235" y="-448" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="235" y="-437" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
+<text text-anchor="start" x="235" y="-525" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
+<text text-anchor="start" x="235" y="-514" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
+<text text-anchor="start" x="235" y="-503" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="235" y="-492" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="235" y="-481" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</a>
</g>
</g>
<!-- Node6->Node3 -->
<g id="edge4" class="edge">
<title>Node6->Node3</title>
-<path fill="none" stroke="#404040" d="M334.2545,-429.6123C339.5928,-397.2712 345.8082,-359.6159 351.8917,-322.7603"/>
-<polygon fill="none" stroke="#404040" points="351.9065,-322.6699 348.9371,-316.0985 353.8609,-310.8301 356.8303,-317.4014 351.9065,-322.6699"/>
-<text text-anchor="middle" x="369.5" y="-332" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #exec_</text>
+<path fill="none" stroke="#404040" d="M333.416,-473.5896C338.3984,-441.5776 344.2212,-404.1665 350.0181,-366.9211"/>
+<polygon fill="none" stroke="#404040" points="350.0527,-366.6986 347.023,-360.1548 351.8982,-354.8413 354.9279,-361.3851 350.0527,-366.6986"/>
+<text text-anchor="middle" x="368.5" y="-376" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #exec_</text>
</g>
<!-- Node7 -->
<g id="node5" class="node">
<title>Node7</title>
<g id="a_node5"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="430.5,-408 430.5,-630 564.5,-630 564.5,-408 430.5,-408"/>
-<text text-anchor="middle" x="497.5" y="-618" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="430.5,-611 564.5,-611 "/>
-<text text-anchor="start" x="438.5" y="-599" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="430.5,-592 564.5,-592 "/>
-<text text-anchor="start" x="438.5" y="-580" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="438.5" y="-569" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="438.5" y="-558" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="438.5" y="-547" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="438.5" y="-536" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="438.5" y="-525" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
-<text text-anchor="start" x="438.5" y="-514" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="438.5" y="-503" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="438.5" y="-492" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="438.5" y="-481" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="438.5" y="-470" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="438.5" y="-459" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="438.5" y="-448" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="438.5" y="-437" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="438.5" y="-426" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="438.5" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<polygon fill="#ffffff" stroke="#000000" points="430.5,-452 430.5,-674 564.5,-674 564.5,-452 430.5,-452"/>
+<text text-anchor="middle" x="497.5" y="-662" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="430.5,-655 564.5,-655 "/>
+<text text-anchor="start" x="438.5" y="-643" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="430.5,-636 564.5,-636 "/>
+<text text-anchor="start" x="438.5" y="-624" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="438.5" y="-613" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="438.5" y="-602" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="438.5" y="-591" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="438.5" y="-580" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="438.5" y="-569" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
+<text text-anchor="start" x="438.5" y="-558" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="438.5" y="-547" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="438.5" y="-536" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="438.5" y="-525" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="438.5" y="-514" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="438.5" y="-503" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="438.5" y="-492" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="438.5" y="-481" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="438.5" y="-470" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="438.5" y="-459" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
</a>
</g>
</g>
<!-- Node7->Node3 -->
<g id="edge5" class="edge">
<title>Node7->Node3</title>
-<path fill="none" stroke="#404040" d="M461.4549,-407.9629C452.6593,-380.8679 443.0574,-351.289 433.6228,-322.2259"/>
-<polygon fill="none" stroke="#404040" points="433.5821,-322.1001 427.9249,-317.6283 429.8769,-310.6864 435.534,-315.1582 433.5821,-322.1001"/>
-<text text-anchor="middle" x="483" y="-332" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #return_register_</text>
+<path fill="none" stroke="#404040" d="M463.4487,-451.7561C455.2453,-424.956 446.2531,-395.5791 437.2979,-366.3229"/>
+<polygon fill="none" stroke="#404040" points="437.2479,-366.1594 431.6669,-361.5929 433.7356,-354.6849 439.3166,-359.2514 437.2479,-366.1594"/>
+<text text-anchor="middle" x="487" y="-376" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #return_register_</text>
</g>
<!-- Node8 -->
<g id="node6" class="node">
<title>Node8</title>
<g id="a_node6"><a xlink:href="classtvm_1_1runtime_1_1ObjectPtr.html" target="_top" xlink:title="{tvm::runtime::ObjectPtr\l\< tvm::runtime::Object \>\n||+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ~ObjectPtr()\l+ swap()\l+ get()\l+ operator-\>()\land 11 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="427.5,-832 427.5,-1010 567.5,-1010 567.5,-832 427.5,-832"/>
-<text text-anchor="start" x="435.5" y="-998" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
-<text text-anchor="middle" x="497.5" y="-987" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
-<polyline fill="none" stroke="#000000" points="427.5,-980 567.5,-980 "/>
-<text text-anchor="middle" x="497.5" y="-968" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="427.5,-961 567.5,-961 "/>
+<polygon fill="#ffffff" stroke="#000000" points="427.5,-876 427.5,-1054 567.5,-1054 567.5,-876 427.5,-876"/>
+<text text-anchor="start" x="435.5" y="-1042" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
+<text text-anchor="middle" x="497.5" y="-1031" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
+<polyline fill="none" stroke="#000000" points="427.5,-1024 567.5,-1024 "/>
+<text text-anchor="middle" x="497.5" y="-1012" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="427.5,-1005 567.5,-1005 "/>
+<text text-anchor="start" x="435.5" y="-993" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="435.5" y="-982" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="435.5" y="-971" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="435.5" y="-960" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="435.5" y="-949" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="435.5" y="-938" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="435.5" y="-927" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="435.5" y="-916" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="435.5" y="-905" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="435.5" y="-894" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="435.5" y="-883" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
-<text text-anchor="start" x="435.5" y="-872" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
-<text text-anchor="start" x="435.5" y="-861" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="435.5" y="-850" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="435.5" y="-839" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
+<text text-anchor="start" x="435.5" y="-927" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
+<text text-anchor="start" x="435.5" y="-916" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
+<text text-anchor="start" x="435.5" y="-905" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="435.5" y="-894" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="435.5" y="-883" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</a>
</g>
</g>
<!-- Node8->Node7 -->
<g id="edge6" class="edge">
<title>Node8->Node7</title>
-<path fill="none" stroke="#404040" d="M497.5,-831.7832C497.5,-776.0511 497.5,-703.5072 497.5,-642.3158"/>
-<polygon fill="none" stroke="#404040" points="497.5001,-642.2372 493.5,-636.2373 497.5,-630.2372 501.5,-636.2372 497.5001,-642.2372"/>
-<text text-anchor="middle" x="517" y="-701" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
+<path fill="none" stroke="#404040" d="M497.5,-875.7832C497.5,-820.0511 497.5,-747.5072 497.5,-686.3158"/>
+<polygon fill="none" stroke="#404040" points="497.5001,-686.2372 493.5,-680.2373 497.5,-674.2372 501.5,-680.2372 497.5001,-686.2372"/>
+<text text-anchor="middle" x="517" y="-745" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
</g>
<!-- Node9 -->
<g id="node7" class="node">
<title>Node9</title>
<g id="a_node7"><a xlink:href="structtvm_1_1runtime_1_1vm_1_1Instruction.html" target="_top" xlink:title="A single virtual machine instruction. ">
-<polygon fill="#ffffff" stroke="#000000" points="582.5,-358.5 582.5,-679.5 742.5,-679.5 742.5,-358.5 582.5,-358.5"/>
-<text text-anchor="middle" x="662.5" y="-667.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Instruction</text>
-<polyline fill="none" stroke="#000000" points="582.5,-660.5 742.5,-660.5 "/>
-<text text-anchor="start" x="590.5" y="-648.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ op</text>
-<text text-anchor="start" x="590.5" y="-637.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ dst</text>
-<text text-anchor="start" x="590.5" y="-626.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ storage</text>
-<text text-anchor="start" x="590.5" y="-615.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ offset</text>
-<text text-anchor="start" x="590.5" y="-604.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ndim</text>
-<text text-anchor="start" x="590.5" y="-593.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ shape</text>
-<text text-anchor="start" x="590.5" y="-582.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ dtype</text>
-<text text-anchor="start" x="590.5" y="-571.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ alloc_tensor</text>
-<text text-anchor="start" x="590.5" y="-560.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ shape_register</text>
-<text text-anchor="start" x="590.5" y="-549.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ alloc_tensor_reg</text>
-<text text-anchor="start" x="590.5" y="-538.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 44 more...</text>
-<polyline fill="none" stroke="#000000" points="582.5,-531.5 742.5,-531.5 "/>
-<text text-anchor="start" x="590.5" y="-519.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Instruction()</text>
-<text text-anchor="start" x="590.5" y="-508.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Instruction()</text>
-<text text-anchor="start" x="590.5" y="-497.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="590.5" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~Instruction()</text>
-<text text-anchor="start" x="590.5" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Ret()</text>
-<text text-anchor="start" x="590.5" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Fatal()</text>
-<text text-anchor="start" x="590.5" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InvokePacked()</text>
-<text text-anchor="start" x="590.5" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ AllocTensor()</text>
-<text text-anchor="start" x="590.5" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ AllocTensorReg()</text>
-<text text-anchor="start" x="590.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ AllocADT()</text>
-<text text-anchor="start" x="590.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ AllocClosure()</text>
-<text text-anchor="start" x="590.5" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetField()</text>
-<text text-anchor="start" x="590.5" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTag()</text>
-<text text-anchor="start" x="590.5" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ If()</text>
-<text text-anchor="start" x="590.5" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
+<polygon fill="#ffffff" stroke="#000000" points="582.5,-402.5 582.5,-723.5 742.5,-723.5 742.5,-402.5 582.5,-402.5"/>
+<text text-anchor="middle" x="662.5" y="-711.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Instruction</text>
+<polyline fill="none" stroke="#000000" points="582.5,-704.5 742.5,-704.5 "/>
+<text text-anchor="start" x="590.5" y="-692.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ op</text>
+<text text-anchor="start" x="590.5" y="-681.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ dst</text>
+<text text-anchor="start" x="590.5" y="-670.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ storage</text>
+<text text-anchor="start" x="590.5" y="-659.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ offset</text>
+<text text-anchor="start" x="590.5" y="-648.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ndim</text>
+<text text-anchor="start" x="590.5" y="-637.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ shape</text>
+<text text-anchor="start" x="590.5" y="-626.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ dtype</text>
+<text text-anchor="start" x="590.5" y="-615.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ alloc_tensor</text>
+<text text-anchor="start" x="590.5" y="-604.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ shape_register</text>
+<text text-anchor="start" x="590.5" y="-593.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ alloc_tensor_reg</text>
+<text text-anchor="start" x="590.5" y="-582.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 44 more...</text>
+<polyline fill="none" stroke="#000000" points="582.5,-575.5 742.5,-575.5 "/>
+<text text-anchor="start" x="590.5" y="-563.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Instruction()</text>
+<text text-anchor="start" x="590.5" y="-552.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Instruction()</text>
+<text text-anchor="start" x="590.5" y="-541.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="590.5" y="-530.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~Instruction()</text>
+<text text-anchor="start" x="590.5" y="-519.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Ret()</text>
+<text text-anchor="start" x="590.5" y="-508.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Fatal()</text>
+<text text-anchor="start" x="590.5" y="-497.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InvokePacked()</text>
+<text text-anchor="start" x="590.5" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ AllocTensor()</text>
+<text text-anchor="start" x="590.5" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ AllocTensorReg()</text>
+<text text-anchor="start" x="590.5" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ AllocADT()</text>
+<text text-anchor="start" x="590.5" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ AllocClosure()</text>
+<text text-anchor="start" x="590.5" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetField()</text>
+<text text-anchor="start" x="590.5" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTag()</text>
+<text text-anchor="start" x="590.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ If()</text>
+<text text-anchor="start" x="590.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</a>
</g>
</g>
<!-- Node9->Node3 -->
<g id="edge7" class="edge">
<title>Node9->Node3</title>
-<path fill="none" stroke="#404040" d="M582.4862,-370.6597C579.527,-366.3456 576.529,-362.1156 573.5,-358 539.5693,-311.898 495.8846,-265.429 458.5626,-228.6546"/>
-<polygon fill="none" stroke="#404040" points="458.2957,-228.3935 451.2094,-227.0573 449.7174,-220.0022 456.8036,-221.3384 458.2957,-228.3935"/>
-<text text-anchor="middle" x="579.5" y="-332" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #code_</text>
+<path fill="none" stroke="#404040" d="M582.4749,-415.2711C579.5087,-410.7574 576.5138,-406.3229 573.5,-402 542.0677,-356.9138 503.137,-310.4125 468.4183,-271.5075"/>
+<polygon fill="none" stroke="#404040" points="468.1711,-271.2321 461.1865,-269.4388 460.1555,-262.3018 467.1401,-264.0951 468.1711,-271.2321"/>
+<text text-anchor="middle" x="578.5" y="-376" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #code_</text>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine__inherit__graph.svg
index 6d6249f4fa..80e52b45b4 100644
--- a/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1runtime_1_1vm_1_1VirtualMachine__inherit__graph.svg
@@ -4,130 +4,134 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::runtime::vm::VirtualMachine Pages: 1 -->
-<svg width="217pt" height="1046pt"
- viewBox="0.00 0.00 217.00 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)">
+<svg width="217pt" height="1090pt"
+ viewBox="0.00 0.00 217.00 1090.00" 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 1086)">
<title>tvm::runtime::vm::VirtualMachine</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1042 213,-1042 213,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1086 213,-1086 213,4 -4,4"/>
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="34.5,-.5 34.5,-343.5 174.5,-343.5 174.5,-.5 34.5,-.5"/>
-<text text-anchor="start" x="42.5" y="-331.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Virtual</text>
-<text text-anchor="middle" x="104.5" y="-320.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Machine</text>
-<polyline fill="none" stroke="#000000" points="34.5,-313.5 174.5,-313.5 "/>
-<text text-anchor="start" x="42.5" y="-301.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># packed_funcs_</text>
-<text text-anchor="start" x="42.5" y="-290.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># frames_</text>
-<text text-anchor="start" x="42.5" y="-279.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># func_index_</text>
-<text text-anchor="start" x="42.5" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># code_</text>
-<text text-anchor="start" x="42.5" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># pc_</text>
-<text text-anchor="start" x="42.5" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># return_register_</text>
-<text text-anchor="start" x="42.5" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># exec_</text>
-<text text-anchor="start" x="42.5" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># inputs_</text>
-<text text-anchor="start" x="42.5" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># devices_</text>
-<text text-anchor="start" x="42.5" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># allocators_</text>
-<text text-anchor="start" x="42.5" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># const_pool_</text>
-<polyline fill="none" stroke="#000000" points="34.5,-184.5 174.5,-184.5 "/>
-<text text-anchor="start" x="42.5" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="42.5" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~VirtualMachine()</text>
-<text text-anchor="start" x="42.5" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
-<text text-anchor="start" x="42.5" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VirtualMachine()</text>
-<text text-anchor="start" x="42.5" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadExecutable()</text>
-<text text-anchor="start" x="42.5" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PushFrame()</text>
-<text text-anchor="start" x="42.5" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PopFrame()</text>
-<text text-anchor="start" x="42.5" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># WriteRegister()</text>
-<text text-anchor="start" x="42.5" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ReadRegister()</text>
-<text text-anchor="start" x="42.5" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># LoadScalarInt()</text>
-<text text-anchor="start" x="42.5" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
-<text text-anchor="start" x="42.5" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
-<text text-anchor="start" x="42.5" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># InvokePacked()</text>
-<text text-anchor="start" x="42.5" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Init()</text>
-<text text-anchor="start" x="42.5" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># RunLoop()</text>
-<text text-anchor="start" x="42.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 7 more...</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="24,-.5 24,-387.5 185,-387.5 185,-.5 24,-.5"/>
+<text text-anchor="start" x="32" y="-375.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::vm::Virtual</text>
+<text text-anchor="middle" x="104.5" y="-364.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Machine</text>
+<polyline fill="none" stroke="#000000" points="24,-357.5 185,-357.5 "/>
+<text text-anchor="start" x="32" y="-345.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># packed_funcs_</text>
+<text text-anchor="start" x="32" y="-334.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># frames_</text>
+<text text-anchor="start" x="32" y="-323.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># func_index_</text>
+<text text-anchor="start" x="32" y="-312.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># code_</text>
+<text text-anchor="start" x="32" y="-301.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># pc_</text>
+<text text-anchor="start" x="32" y="-290.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># return_register_</text>
+<text text-anchor="start" x="32" y="-279.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># exec_</text>
+<text text-anchor="start" x="32" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># inputs_</text>
+<text text-anchor="start" x="32" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># set_outputs_enabled_</text>
+<text text-anchor="start" x="32" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># preresult_op_index_</text>
+<text text-anchor="start" x="32" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># output_tensor_reg_indices_</text>
+<text text-anchor="start" x="32" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># outputs_</text>
+<text text-anchor="start" x="32" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># devices_</text>
+<text text-anchor="start" x="32" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># allocators_</text>
+<text text-anchor="start" x="32" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># const_pool_</text>
+<polyline fill="none" stroke="#000000" points="24,-184.5 185,-184.5 "/>
+<text text-anchor="start" x="32" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="32" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~VirtualMachine()</text>
+<text text-anchor="start" x="32" y="-150.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
+<text text-anchor="start" x="32" y="-139.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VirtualMachine()</text>
+<text text-anchor="start" x="32" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ LoadExecutable()</text>
+<text text-anchor="start" x="32" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PushFrame()</text>
+<text text-anchor="start" x="32" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># PopFrame()</text>
+<text text-anchor="start" x="32" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># WriteRegister()</text>
+<text text-anchor="start" x="32" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ReadRegister()</text>
+<text text-anchor="start" x="32" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># LoadScalarInt()</text>
+<text text-anchor="start" x="32" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="32" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="32" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Invoke()</text>
+<text text-anchor="start" x="32" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># InvokePacked()</text>
+<text text-anchor="start" x="32" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># Init()</text>
+<text text-anchor="start" x="32" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</g>
<!-- Node1 -->
<g id="node2" class="node">
<title>Node1</title>
<g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1ModuleNode.html" target="_top" xlink:title="Base container of module. ">
-<polygon fill="#ffffff" stroke="#000000" points="0,-380.5 0,-602.5 209,-602.5 209,-380.5 0,-380.5"/>
-<text text-anchor="middle" x="104.5" y="-590.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ModuleNode</text>
-<polyline fill="none" stroke="#000000" points="0,-583.5 209,-583.5 "/>
-<text text-anchor="start" x="8" y="-571.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="8" y="-560.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="8" y="-549.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># imports_</text>
-<polyline fill="none" stroke="#000000" points="0,-542.5 209,-542.5 "/>
-<text text-anchor="start" x="8" y="-530.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ModuleNode()</text>
-<text text-anchor="start" x="8" y="-519.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
-<text text-anchor="start" x="8" y="-508.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="8" y="-497.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
-<text text-anchor="start" x="8" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
-<text text-anchor="start" x="8" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetSource()</text>
-<text text-anchor="start" x="8" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFormat()</text>
-<text text-anchor="start" x="8" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
-<text text-anchor="start" x="8" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Import()</text>
-<text text-anchor="start" x="8" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFuncFromEnv()</text>
-<text text-anchor="start" x="8" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ imports()</text>
-<text text-anchor="start" x="8" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsDSOExportable()</text>
-<text text-anchor="start" x="8" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ImplementsFunction()</text>
-<text text-anchor="start" x="8" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
+<polygon fill="#ffffff" stroke="#000000" points="0,-424.5 0,-646.5 209,-646.5 209,-424.5 0,-424.5"/>
+<text text-anchor="middle" x="104.5" y="-634.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ModuleNode</text>
+<polyline fill="none" stroke="#000000" points="0,-627.5 209,-627.5 "/>
+<text text-anchor="start" x="8" y="-615.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="8" y="-604.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="8" y="-593.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># imports_</text>
+<polyline fill="none" stroke="#000000" points="0,-586.5 209,-586.5 "/>
+<text text-anchor="start" x="8" y="-574.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ModuleNode()</text>
+<text text-anchor="start" x="8" y="-563.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_key()</text>
+<text text-anchor="start" x="8" y="-552.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="8" y="-541.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToFile()</text>
+<text text-anchor="start" x="8" y="-530.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SaveToBinary()</text>
+<text text-anchor="start" x="8" y="-519.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetSource()</text>
+<text text-anchor="start" x="8" y="-508.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFormat()</text>
+<text text-anchor="start" x="8" y="-497.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFunction()</text>
+<text text-anchor="start" x="8" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Import()</text>
+<text text-anchor="start" x="8" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetFuncFromEnv()</text>
+<text text-anchor="start" x="8" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ imports()</text>
+<text text-anchor="start" x="8" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsDSOExportable()</text>
+<text text-anchor="start" x="8" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ImplementsFunction()</text>
+<text text-anchor="start" x="8" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
</a>
</g>
</g>
<!-- Node1->Node0 -->
<g id="edge1" class="edge">
<title>Node1->Node0</title>
-<path fill="none" stroke="#191970" d="M104.5,-370.0869C104.5,-361.401 104.5,-352.5543 104.5,-343.6582"/>
-<polygon fill="none" stroke="#191970" points="101.0001,-370.2029 104.5,-380.2029 108.0001,-370.203 101.0001,-370.2029"/>
+<path fill="none" stroke="#191970" d="M104.5,-414.1206C104.5,-405.4978 104.5,-396.6912 104.5,-387.7996"/>
+<polygon fill="none" stroke="#191970" points="101.0001,-414.1526 104.5,-424.1527 108.0001,-414.1527 101.0001,-414.1526"/>
</g>
<!-- Node2 -->
<g id="node3" class="node">
<title>Node2</title>
<g id="a_node3"><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="13,-639.5 13,-1037.5 196,-1037.5 196,-639.5 13,-639.5"/>
-<text text-anchor="middle" x="104.5" y="-1025.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
-<polyline fill="none" stroke="#000000" points="13,-1018.5 196,-1018.5 "/>
-<text text-anchor="start" x="21" y="-1006.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="21" y="-995.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
-<text text-anchor="start" x="21" y="-984.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
-<text text-anchor="start" x="21" y="-973.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
-<text text-anchor="start" x="21" y="-962.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
-<text text-anchor="start" x="21" y="-951.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
-<text text-anchor="start" x="21" y="-940.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
-<text text-anchor="start" x="21" y="-929.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="21" y="-918.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="21" y="-907.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
-<text text-anchor="start" x="21" y="-896.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="21" y="-885.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="21" y="-874.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
-<text text-anchor="start" x="21" y="-863.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
-<text text-anchor="start" x="21" y="-852.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
-<polyline fill="none" stroke="#000000" points="13,-845.5 196,-845.5 "/>
-<text text-anchor="start" x="21" y="-833.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
-<text text-anchor="start" x="21" y="-822.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
-<text text-anchor="start" x="21" y="-811.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
-<text text-anchor="start" x="21" y="-800.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
-<text text-anchor="start" x="21" y="-789.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="21" y="-778.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-767.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-756.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-745.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="21" y="-734.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="21" y="-723.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
-<text text-anchor="start" x="21" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
-<text text-anchor="start" x="21" y="-701.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
-<text text-anchor="start" x="21" y="-690.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
-<text text-anchor="start" x="21" y="-679.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
-<text text-anchor="start" x="21" y="-668.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
-<text text-anchor="start" x="21" y="-657.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
-<text text-anchor="start" x="21" y="-646.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
+<polygon fill="#ffffff" stroke="#000000" points="13,-683.5 13,-1081.5 196,-1081.5 196,-683.5 13,-683.5"/>
+<text text-anchor="middle" x="104.5" y="-1069.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
+<polyline fill="none" stroke="#000000" points="13,-1062.5 196,-1062.5 "/>
+<text text-anchor="start" x="21" y="-1050.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="21" y="-1039.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
+<text text-anchor="start" x="21" y="-1028.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
+<text text-anchor="start" x="21" y="-1017.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
+<text text-anchor="start" x="21" y="-1006.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
+<text text-anchor="start" x="21" y="-995.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
+<text text-anchor="start" x="21" y="-984.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
+<text text-anchor="start" x="21" y="-973.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
+<text text-anchor="start" x="21" y="-962.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="21" y="-951.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="21" y="-940.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="21" y="-929.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="21" y="-918.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
+<text text-anchor="start" x="21" y="-907.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
+<text text-anchor="start" x="21" y="-896.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
+<polyline fill="none" stroke="#000000" points="13,-889.5 196,-889.5 "/>
+<text text-anchor="start" x="21" y="-877.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
+<text text-anchor="start" x="21" y="-866.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
+<text text-anchor="start" x="21" y="-855.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
+<text text-anchor="start" x="21" y="-844.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
+<text text-anchor="start" x="21" y="-833.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="21" y="-822.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-811.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-800.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-789.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="21" y="-778.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="21" y="-767.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
+<text text-anchor="start" x="21" y="-756.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
+<text text-anchor="start" x="21" y="-745.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
+<text text-anchor="start" x="21" y="-734.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="21" y="-723.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
+<text text-anchor="start" x="21" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
+<text text-anchor="start" x="21" y="-701.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
+<text text-anchor="start" x="21" y="-690.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
</a>
</g>
</g>
<!-- Node2->Node1 -->
<g id="edge2" class="edge">
<title>Node2->Node1</title>
-<path fill="none" stroke="#191970" d="M104.5,-629.1635C104.5,-620.1306 104.5,-611.2331 104.5,-602.575"/>
-<polygon fill="none" stroke="#191970" points="101.0001,-629.414 104.5,-639.4141 108.0001,-629.4141 101.0001,-629.414"/>
+<path fill="none" stroke="#191970" d="M104.5,-673.1635C104.5,-664.1306 104.5,-655.2331 104.5,-646.575"/>
+<polygon fill="none" stroke="#191970" points="101.0001,-673.414 104.5,-683.4141 108.0001,-673.4141 101.0001,-673.414"/>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/functions_func_i.html b/docs/reference/api/doxygen/functions_func_i.html
index 79a6277b54..88c60cd26d 100644
--- a/docs/reference/api/doxygen/functions_func_i.html
+++ b/docs/reference/api/doxygen/functions_func_i.html
@@ -236,7 +236,7 @@ $(function() {
</li>
<li>Invoke()
: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#acb19406a24fa95bf39a29d15ad6be256">tvm::runtime::vm::Instruction</a>
-, <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa5f4724e2e702ef9d5c34e85dec53b02">tvm::runtime::vm::VirtualMachine</a>
+, <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6cc5773f6bc5066ddab180a443df72a9">tvm::runtime::vm::VirtualMachine</a>
</li>
<li>InvokeClosure()
: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#aff2701f8ac1a6232115e73fbb3fe522a">tvm::runtime::vm::Instruction</a>
@@ -396,7 +396,7 @@ $(function() {
</li>
<li>iterator()
: <a class="el" href="classtvm_1_1runtime_1_1Map_1_1iterator.html#ad8b40ddeffccb6f221601eda70202f9a">tvm::runtime::Map< K, V, typename, typename >::iterator</a>
-, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#ad605c9f9aaed23e669c2a3c595d08ba4">tvm::runtime::MapNode::iterator</a>
+, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a75e3f2657cdb7cc613bf922429983165">tvm::runtime::MapNode::iterator</a>
</li>
<li>iterator_base()
: <a class="el" href="classtvm_1_1support_1_1Span_1_1iterator__base.html#a8280a97672c014b1d2005158896ed43a">tvm::support::Span< T, W >::iterator_base< W1 ></a>
@@ -408,7 +408,7 @@ $(function() {
: <a class="el" href="classtvm_1_1arith_1_1IterMark.html#a7b46a2bc2460f43e529a6fc65a0a618d">tvm::arith::IterMark</a>
</li>
<li>IterSplitExpr()
-: <a class="el" href="classtvm_1_1arith_1_1IterSplitExpr.html#a754a9d8338aa2d2b5fac9e10c95c9128">tvm::arith::IterSplitExpr</a>
+: <a class="el" href="classtvm_1_1arith_1_1IterSplitExpr.html#af919631fd9bfb7726d0a867ee9f0e6f5">tvm::arith::IterSplitExpr</a>
</li>
<li>IterSumExpr()
: <a class="el" href="classtvm_1_1arith_1_1IterSumExpr.html#a1b9f8013f3978bafe4da3a6cad65fb36">tvm::arith::IterSumExpr</a>
@@ -420,7 +420,7 @@ $(function() {
: <a class="el" href="classtvm_1_1te_1_1IterVarAttr.html#a5549479b7e3ce243d89b219b0dd7ef71">tvm::te::IterVarAttr</a>
</li>
<li>IterVarRelation()
-: <a class="el" href="classtvm_1_1te_1_1IterVarRelation.html#a3e611ee0870d9a542b8deb79575dbf66">tvm::te::IterVarRelation</a>
+: <a class="el" href="classtvm_1_1te_1_1IterVarRelation.html#a4b50caede957f1cb50587ce15a87109f">tvm::te::IterVarRelation</a>
</li>
</ul>
</div><!-- contents -->
diff --git a/docs/reference/api/doxygen/functions_func_p.html b/docs/reference/api/doxygen/functions_func_p.html
index 9c8a667495..1401b669f4 100644
--- a/docs/reference/api/doxygen/functions_func_p.html
+++ b/docs/reference/api/doxygen/functions_func_p.html
@@ -246,6 +246,9 @@ $(function() {
<li>PrintIndent()
: <a class="el" href="classtvm_1_1ReprPrinter.html#a9c5941e7c4e24c9880dbd340cc226bf4">tvm::ReprPrinter</a>
</li>
+<li>PrintInfoAndSetInputArgs()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ac2ca0dc6162002d400e56ccc4c41fb9c">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>PrintStepsAsPython()
: <a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeDAG.html#ace0f0f385d5d3179dd5dc0a1f35990b4">tvm::auto_scheduler::ComputeDAG</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_func_r.html b/docs/reference/api/doxygen/functions_func_r.html
index f0abe7b435..bf42ab47fa 100644
--- a/docs/reference/api/doxygen/functions_func_r.html
+++ b/docs/reference/api/doxygen/functions_func_r.html
@@ -296,7 +296,7 @@ $(function() {
, <a class="el" href="classtvm_1_1relay_1_1MixedModeMutator.html#a4c93a9094db80cace013ef02e6bcd724">tvm::relay::MixedModeMutator</a>
</li>
<li>Rewrite_()
-: <a class="el" href="classtvm_1_1relay_1_1ExprRewriter.html#afd8e949e00f51987ee9062c0b67c5f70">tvm::relay::ExprRewriter</a>
+: <a class="el" href="classtvm_1_1relay_1_1ExprRewriter.html#a75b4f0d342f6bd253b4f0b5d036a9156">tvm::relay::ExprRewriter</a>
, <a class="el" href="classtvm_1_1relay_1_1MixedModeMutator.html#a3b53908f4b8cc3708ca75892e47f0929">tvm::relay::MixedModeMutator</a>
</li>
<li>RewriteCooperativeFetch()
@@ -377,7 +377,7 @@ $(function() {
: <a class="el" href="classtvm_1_1auto__scheduler_1_1SearchPolicyNode.html#a4bf8f2f816014b03ebea564d50afeba9">tvm::auto_scheduler::SearchPolicyNode</a>
</li>
<li>RunLoop()
-: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ad83dfc94ba5e62875df9e780c750487b">tvm::runtime::vm::VirtualMachine</a>
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a08164ef76393a4efb002c1ea6b8ae447">tvm::runtime::vm::VirtualMachine</a>
</li>
<li>RunnerFuture()
: <a class="el" href="classtvm_1_1meta__schedule_1_1RunnerFuture.html#a88baeedd7be0b5cc46083f75a318317f">tvm::meta_schedule::RunnerFuture</a>
diff --git a/docs/reference/api/doxygen/functions_func_s.html b/docs/reference/api/doxygen/functions_func_s.html
index 28af8fbacd..bdd9d1940d 100644
--- a/docs/reference/api/doxygen/functions_func_s.html
+++ b/docs/reference/api/doxygen/functions_func_s.html
@@ -410,6 +410,12 @@ $(function() {
<li>SetOneInput()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ab66c1484cfb630914dd41da36ab91db1">tvm::runtime::vm::VirtualMachine</a>
</li>
+<li>SetOutputs()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a2ee3a67f145ed44cabfb4d456c048445">tvm::runtime::vm::VirtualMachine</a>
+</li>
+<li>SetOutputTensorsToRegister()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a95a0552177a93f4839ab431756efeaf3">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>SetScope()
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#aa4760135d373af488a08aaeba7114c48">tvm::tir::ScheduleNode</a>
</li>
@@ -441,7 +447,7 @@ $(function() {
: <a class="el" href="classtvm_1_1relay_1_1ShapePattern.html#a853201a9d5df8de96713a58c292e8698">tvm::relay::ShapePattern</a>
</li>
<li>ShapeTuple()
-: <a class="el" href="classtvm_1_1runtime_1_1ShapeTuple.html#a08d3ed30940fe54e2380eb933401cd05">tvm::runtime::ShapeTuple</a>
+: <a class="el" href="classtvm_1_1runtime_1_1ShapeTuple.html#a6836ad757cbcac207ddf025a74ac2ef2">tvm::runtime::ShapeTuple</a>
</li>
<li>SHashReduce()
: <a class="el" href="classtvm_1_1arith_1_1IntConstraintsNode.html#add6e128afc66485e71854a8800c90c7a">tvm::arith::IntConstraintsNode</a>
@@ -670,8 +676,8 @@ $(function() {
: <a class="el" href="classtvm_1_1auto__scheduler_1_1SplitStep.html#a64ed86582a56a2645b3e4eb44ecb31af">tvm::auto_scheduler::SplitStep</a>
</li>
<li>Stage()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1Stage.html#a39ffbb1b4e189180bc4067e74965f42b">tvm::auto_scheduler::Stage</a>
-, <a class="el" href="classtvm_1_1te_1_1Stage.html#afec82602b9321c489b88632a005335f8">tvm::te::Stage</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1Stage.html#af0643fe8c1298451c9a322f915c48843">tvm::auto_scheduler::Stage</a>
+, <a class="el" href="classtvm_1_1te_1_1Stage.html#a1ecdc9a000be62c9cc26a96d4c33e36e">tvm::te::Stage</a>
</li>
<li>Start()
: <a class="el" href="classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#a44fadfb7b0f961a7fb2275e3b5dbcd88">tvm::runtime::profiling::MetricCollectorNode</a>
@@ -740,7 +746,7 @@ $(function() {
: <a class="el" href="classtvm_1_1tir_1_1Store.html#a2c4278b8bcdae57ada2022ecc7c290c3">tvm::tir::Store</a>
</li>
<li>Str()
-: <a class="el" href="classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a789d7d73bd4d94612fa2a84c16b26b89">tvm::script::printer::LiteralDoc</a>
+: <a class="el" href="classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a3511ed66e343f6db16cbd72feda03d5c">tvm::script::printer::LiteralDoc</a>
</li>
<li>str()
: <a class="el" href="classtvm_1_1TargetNode.html#a30cd67db46a9c4b098a8ba38fff22e26">tvm::TargetNode</a>
diff --git a/docs/reference/api/doxygen/functions_func_t.html b/docs/reference/api/doxygen/functions_func_t.html
index 2c600ad25d..92c89285e3 100644
--- a/docs/reference/api/doxygen/functions_func_t.html
+++ b/docs/reference/api/doxygen/functions_func_t.html
@@ -1210,7 +1210,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypeData.html#a0a98fd1095812379d2bd1337db1511c1">tvm::TypeData</a>
</li>
<li>TypedEnvFunc()
-: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a41a6b9014d0feeb628ca7edfd0d26f0b">tvm::TypedEnvFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a0d72a6fa7263821c14bcd37837998ed9">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#afd8ee9dd9648c19b468bb4b0b00e8e4e">tvm::runtime::TypedPackedFunc< R(Args...)></a>
@@ -1236,7 +1236,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypeRelation.html#ac26b1897eab8197ed26606ab81b7403b">tvm::TypeRelation</a>
</li>
<li>TypeReporter()
-: <a class="el" href="classtvm_1_1TypeReporter.html#a8e7e05a07f9f7ad9bea91f27afac9051">tvm::TypeReporter</a>
+: <a class="el" href="classtvm_1_1TypeReporter.html#aa3dc38a3c84d324d0b3a9f358460a091">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 611cae9ff1..4b4e0f203d 100644
--- a/docs/reference/api/doxygen/functions_func_u.html
+++ b/docs/reference/api/doxygen/functions_func_u.html
@@ -106,7 +106,7 @@ $(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_func_v.html b/docs/reference/api/doxygen/functions_func_v.html
index cfbeb72d8c..d41f1a3755 100644
--- a/docs/reference/api/doxygen/functions_func_v.html
+++ b/docs/reference/api/doxygen/functions_func_v.html
@@ -490,7 +490,7 @@ $(function() {
<li>VisitType_()
: <a class="el" href="classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html#aca50c939b0a6d8ebea33865c26e82729">tvm::TypeFunctor< R(const Type &n, Args...)></a>
, <a class="el" href="classtvm_1_1TypeMutator.html#a0d7ff530827c63fb3eb18cb720305dca">tvm::TypeMutator</a>
-, <a class="el" href="classtvm_1_1TypeVisitor.html#a1e33da035ed09ba49e2cc254f8a033c4">tvm::TypeVisitor</a>
+, <a class="el" href="classtvm_1_1TypeVisitor.html#ac8845fbf58c1a1f0ebc23c7ee403aaab">tvm::TypeVisitor</a>
</li>
<li>VisitTypeDefault_()
: <a class="el" href="classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html#a91553f9e04c39b3821a70ae4f7b0c597">tvm::TypeFunctor< R(const Type &n, Args...)></a>
@@ -509,7 +509,7 @@ $(function() {
: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html#a8f8c990ee4fa7cb7472f5440f2ca3bde">tvm::runtime::vm::VMFrame</a>
</li>
<li>VMFunction()
-: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#af9d2bdcf19642c21bc4909b9e9b6196d">tvm::runtime::vm::VMFunction</a>
+: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#aea763069fe1dd6849ce0d1ec336931e0">tvm::runtime::vm::VMFunction</a>
</li>
<li>Void()
: <a class="el" href="classtvm_1_1runtime_1_1DataType.html#ab8dc0832aff8fd7421884c0fe20a3bfd">tvm::runtime::DataType</a>
diff --git a/docs/reference/api/doxygen/functions_i.html b/docs/reference/api/doxygen/functions_i.html
index 6f5648d203..97b05fdf3e 100644
--- a/docs/reference/api/doxygen/functions_i.html
+++ b/docs/reference/api/doxygen/functions_i.html
@@ -545,8 +545,8 @@ $(function() {
<li>IsPrimal()
: <a class="el" href="classtvm_1_1tir_1_1LayoutAxis.html#a4a8e9b07fbdfccc187ea41141b373ebe">tvm::tir::LayoutAxis</a>
</li>
-<li>IsPrimitiveOp()
-: <a class="el" href="classtvm_1_1OpNode.html#a3ba51353d63c4674eac080a3560a4412">tvm::OpNode</a>
+<li>IsPrimitiveOp
+: <a class="el" href="classtvm_1_1OpNode.html#aee9090e54dff3e72ed272b981e036ae6">tvm::OpNode</a>
</li>
<li>IsRegionCoveredConsumer()
: <a class="el" href="classtvm_1_1tir_1_1ScheduleStateNode.html#a9596efdecacb172c531a53b1f21717ad">tvm::tir::ScheduleStateNode</a>
@@ -617,7 +617,7 @@ $(function() {
<li>iterator
: <a class="el" href="classtvm_1_1runtime_1_1Array.html#a98e5ad633b8195d954c98067213ae29f">tvm::runtime::Array< T, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Map_1_1iterator.html#ad8b40ddeffccb6f221601eda70202f9a">tvm::runtime::Map< K, V, typename, typename >::iterator</a>
-, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#ad605c9f9aaed23e669c2a3c595d08ba4">tvm::runtime::MapNode::iterator</a>
+, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a75e3f2657cdb7cc613bf922429983165">tvm::runtime::MapNode::iterator</a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayAccessor.html#a79703afd52032715cc2d9d4c6830147f">tvm::runtime::metadata::ArrayAccessor< C, Ref ></a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayAccessor_3_01const_01char_01_5_00_01_1_1tvm_1_1runtime_1_1String_01_4.html#a3216d91ef7fb0771463e76c9a0afcd1c">tvm::runtime::metadata::ArrayAccessor< const char *, ::tvm::runtime::String ></a>
, <a class="el" href="classtvm_1_1support_1_1Span.html#af6fbb6a54a3ecf8673146acae0c8228b">tvm::support::Span< T, W ></a>
@@ -646,7 +646,7 @@ $(function() {
: <a class="el" href="classtvm_1_1auto__scheduler_1_1StageNode.html#a65304957db6f84d8d7c90ad553453bb9">tvm::auto_scheduler::StageNode</a>
</li>
<li>IterSplitExpr()
-: <a class="el" href="classtvm_1_1arith_1_1IterSplitExpr.html#a754a9d8338aa2d2b5fac9e10c95c9128">tvm::arith::IterSplitExpr</a>
+: <a class="el" href="classtvm_1_1arith_1_1IterSplitExpr.html#af919631fd9bfb7726d0a867ee9f0e6f5">tvm::arith::IterSplitExpr</a>
</li>
<li>IterSumExpr()
: <a class="el" href="classtvm_1_1arith_1_1IterSumExpr.html#a1b9f8013f3978bafe4da3a6cad65fb36">tvm::arith::IterSumExpr</a>
@@ -655,10 +655,10 @@ $(function() {
: <a class="el" href="classtvm_1_1tir_1_1IterVar.html#a1c0d6998203092c953b7da00f16c5c31">tvm::tir::IterVar</a>
</li>
<li>IterVarAttr()
-: <a class="el" href="classtvm_1_1te_1_1IterVarAttr.html#aa20680587a1c880b659063cd37ba4763">tvm::te::IterVarAttr</a>
+: <a class="el" href="classtvm_1_1te_1_1IterVarAttr.html#a5549479b7e3ce243d89b219b0dd7ef71">tvm::te::IterVarAttr</a>
</li>
<li>IterVarRelation()
-: <a class="el" href="classtvm_1_1te_1_1IterVarRelation.html#a4b50caede957f1cb50587ce15a87109f">tvm::te::IterVarRelation</a>
+: <a class="el" href="classtvm_1_1te_1_1IterVarRelation.html#a3e611ee0870d9a542b8deb79575dbf66">tvm::te::IterVarRelation</a>
</li>
</ul>
</div><!-- contents -->
diff --git a/docs/reference/api/doxygen/functions_k.html b/docs/reference/api/doxygen/functions_k.html
index c66923d1e8..81b83edcd7 100644
--- a/docs/reference/api/doxygen/functions_k.html
+++ b/docs/reference/api/doxygen/functions_k.html
@@ -149,13 +149,13 @@ $(function() {
: <a class="el" href="classtvm_1_1GlobalTypeVarNode.html#a335e232894a68cc1e0ecb766bf4053c7">tvm::GlobalTypeVarNode</a>
, <a class="el" href="classtvm_1_1IncompleteTypeNode.html#ab5f37175c1fd0dbbbedc2edaa23d33dc">tvm::IncompleteTypeNode</a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1MetadataArrayNode.html#a695a21a69be1e72b330abe32c685552e">tvm::runtime::metadata::MetadataArrayNode</a>
+, <a class="el" href="classtvm_1_1script_1_1printer_1_1OperationDocNode.html#a9b996402fa4a7202d749c56ac044e810">tvm::script::printer::OperationDocNode</a>
</li>
<li>Kind
: <a class="el" href="classtvm_1_1script_1_1printer_1_1OperationDocNode.html#ab096bbea749ee994d75230cd8136afc2">tvm::script::printer::OperationDocNode</a>
</li>
<li>kind
-: <a class="el" href="classtvm_1_1script_1_1printer_1_1OperationDocNode.html#a9b996402fa4a7202d749c56ac044e810">tvm::script::printer::OperationDocNode</a>
-, <a class="el" href="classtvm_1_1TargetNode.html#ac19a4ee0f0ec7ea607ec746bc4551b71">tvm::TargetNode</a>
+: <a class="el" href="classtvm_1_1TargetNode.html#ac19a4ee0f0ec7ea607ec746bc4551b71">tvm::TargetNode</a>
, <a class="el" href="classtvm_1_1tir_1_1DependencyNode.html#aeb900845b1ca3fb8787ab183af8389b7">tvm::tir::DependencyNode</a>
, <a class="el" href="classtvm_1_1tir_1_1ForNode.html#a4fe09a4b1fb71a8ae8d5e7c807d8540b">tvm::tir::ForNode</a>
, <a class="el" href="classtvm_1_1tir_1_1InstructionNode.html#a85c4921fdf1ebae5c95e5c4f09467355">tvm::tir::InstructionNode</a>
diff --git a/docs/reference/api/doxygen/functions_o.html b/docs/reference/api/doxygen/functions_o.html
index 170f19db7c..79a1e15235 100644
--- a/docs/reference/api/doxygen/functions_o.html
+++ b/docs/reference/api/doxygen/functions_o.html
@@ -411,12 +411,12 @@ $(function() {
, <a class="el" href="classtvm_1_1Integer.html#ad538a2ae6f636b3ce38fb4162b1c2549">tvm::Integer</a>
, <a class="el" href="classtvm_1_1relay_1_1PatternWildcard.html#aef430b36a4be504969829f800e126245">tvm::relay::PatternWildcard</a>
, <a class="el" href="classtvm_1_1runtime_1_1Array.html#a8f52fa8c97344586060ca735a3b91b39">tvm::runtime::Array< T, typename ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1Map.html#ac62909410a98a078ff01f688cdf70ffe">tvm::runtime::Map< K, V, typename, typename ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Map.html#a6b398835e5160e792634c8ee0783f284">tvm::runtime::Map< K, V, typename, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">tvm::runtime::Object</a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#afda3c65f41e83e1c87145a216f8c846d">tvm::runtime::ObjectPtr< T ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a377e159dbff53b8544a1b3337afc379d">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a98b43ed21bc060868ac03dab520a5da2">tvm::runtime::Optional< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1String.html#a3b3c8614af05adc454f47132e04552ed">tvm::runtime::String</a>
-, <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#ac87c22e4d49e79ce5b36b3aead667fcb">tvm::runtime::TVMRetValue</a>
+, <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#a4993d4b338c28096b56ed3d0d9ae5170">tvm::runtime::TVMRetValue</a>
, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#aa590b3e712e06867805b41aaf17019ed">tvm::runtime::TypedPackedFunc< R(Args...)></a>
, <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a69c12a9470f67ea26e53172f5c9220a1">tvm::runtime::vm::Instruction</a>
, <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#aab332907b9f98876f441f6403b801187">tvm::TypedEnvFunc< R(Args...)></a>
@@ -446,7 +446,7 @@ $(function() {
, <a class="el" href="classtvm_1_1AttrRegistryMapContainerMap.html#a713c3d1884423e3e67e3fdaef2566925">tvm::AttrRegistryMapContainerMap< KeyType ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ADT.html#a88cf389012aad0e129c84c056ae546fc">tvm::runtime::ADT</a>
, <a class="el" href="classtvm_1_1runtime_1_1Array.html#ac84683f61368eb10e26e72a0097cccd7">tvm::runtime::Array< T, typename ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1InplaceArrayBase.html#a4b37b5fcd2285b818e8f623da8b326b2">tvm::runtime::InplaceArrayBase< ArrayType, ElemType ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1InplaceArrayBase.html#a45c91b04c230f7400727b1bc02a93f02">tvm::runtime::InplaceArrayBase< ArrayType, ElemType ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Map.html#a865a58097e473b532b1373bd15a1e91f">tvm::runtime::Map< K, V, typename, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayAccessor.html#a65fcb8067aa37421bb244573a07bb0b7">tvm::runtime::metadata::ArrayAccessor< C, Ref ></a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayAccessor_3_01const_01char_01_5_00_01_1_1tvm_1_1runtime_1_1String_01_4.html#ab5e946c37ae641eb9b541df79a54c3e5">tvm::runtime::metadata::ArrayAccessor< const char *, ::tvm::runtime::String ></a>
@@ -488,7 +488,7 @@ $(function() {
</li>
<li>Optional()
: <a class="el" href="classtvm_1_1relay_1_1DFPattern.html#aa573fa65bf9c4f0ba090225105233136">tvm::relay::DFPattern</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#af684522b40606c8b5e0907fbd103291e">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#ae7344a4b601b13152afff14a8dc52857">tvm::runtime::Optional< T ></a>
</li>
<li>optional_homogeneous_target
: <a class="el" href="classtvm_1_1CompilationConfigNode.html#ac29775462c7f70a3711221871fbd3453">tvm::CompilationConfigNode</a>
@@ -604,6 +604,9 @@ $(function() {
, <a class="el" href="structtvm_1_1relay_1_1AdaptivePool3DAttrs.html#a0c56cb9665840dcc8e949c41d39c710d">tvm::relay::AdaptivePool3DAttrs</a>
, <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a6bb6a1b8be0c078394f2336970aab1af">tvm::runtime::vm::Instruction</a>
</li>
+<li>output_tensor_reg_indices_
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa98e90db9a3ef70c732b5322171023c2">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>outputs()
: <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1MetadataNode.html#a9c58f4dbbbe913f79a76623ea3d8d690">tvm::runtime::metadata::MetadataNode</a>
, <a class="el" href="classtvm_1_1te_1_1HybridOpNode.html#a6ff8e6faa8d01063e32a2c124721df29">tvm::te::HybridOpNode</a>
@@ -611,6 +614,9 @@ $(function() {
, <a class="el" href="classtvm_1_1tir_1_1InstructionNode.html#a745f994b096890961ed67b17f2040bba">tvm::tir::InstructionNode</a>
, <a class="el" href="structTVMMetadata.html#ae98ddb5d3a598ab923d8cadc66d38632">TVMMetadata</a>
</li>
+<li>outputs_
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a43d9a2e6056305a8c14941eb08f2cf29">tvm::runtime::vm::VirtualMachine</a>
+</li>
</ul>
</div><!-- contents -->
<!-- start footer part -->
diff --git a/docs/reference/api/doxygen/functions_p.html b/docs/reference/api/doxygen/functions_p.html
index cec6e777f4..d80b281a90 100644
--- a/docs/reference/api/doxygen/functions_p.html
+++ b/docs/reference/api/doxygen/functions_p.html
@@ -405,12 +405,15 @@ $(function() {
<li>preprocessor
: <a class="el" href="classtvm_1_1TargetKindNode.html#a47f02c66d0f972befdfb29ec592ecba0">tvm::TargetKindNode</a>
</li>
+<li>preresult_op_index_
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a37b4a705186bf76cb9aa5168dcbc3651">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>PreTuning()
: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a53127523582ffdb12f40c9433a577adf">tvm::meta_schedule::PySearchStrategyNode</a>
, <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#ad88e1545e88dc1934c25f4b417077aff">tvm::meta_schedule::SearchStrategyNode</a>
</li>
<li>PrimExpr()
-: <a class="el" href="classtvm_1_1PrimExpr.html#a7f0ca30e951608a0b36a77a66d4d19e0">tvm::PrimExpr</a>
+: <a class="el" href="classtvm_1_1PrimExpr.html#a756d3f8b17b019560946524951ae6118">tvm::PrimExpr</a>
</li>
<li>PrimFunc()
: <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html#ab01a529fafaf9fabdfca170605f7b0f8">tvm::tir::PrimFunc</a>
@@ -452,6 +455,9 @@ $(function() {
<li>PrintIndent()
: <a class="el" href="classtvm_1_1ReprPrinter.html#a9c5941e7c4e24c9880dbd340cc226bf4">tvm::ReprPrinter</a>
</li>
+<li>PrintInfoAndSetInputArgs()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ac2ca0dc6162002d400e56ccc4c41fb9c">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>PrintStepsAsPython()
: <a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeDAG.html#ace0f0f385d5d3179dd5dc0a1f35990b4">tvm::auto_scheduler::ComputeDAG</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_r.html b/docs/reference/api/doxygen/functions_r.html
index ea88091b48..eb2d0d4ed7 100644
--- a/docs/reference/api/doxygen/functions_r.html
+++ b/docs/reference/api/doxygen/functions_r.html
@@ -629,7 +629,7 @@ $(function() {
: <a class="el" href="classtvm_1_1auto__scheduler_1_1SearchPolicyNode.html#a4bf8f2f816014b03ebea564d50afeba9">tvm::auto_scheduler::SearchPolicyNode</a>
</li>
<li>RunLoop()
-: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ad83dfc94ba5e62875df9e780c750487b">tvm::runtime::vm::VirtualMachine</a>
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a08164ef76393a4efb002c1ea6b8ae447">tvm::runtime::vm::VirtualMachine</a>
</li>
<li>runner
: <a class="el" href="classtvm_1_1auto__scheduler_1_1ProgramMeasurerNode.html#a0f7a4a84637fd0309b52f61b65bee158">tvm::auto_scheduler::ProgramMeasurerNode</a>
diff --git a/docs/reference/api/doxygen/functions_s.html b/docs/reference/api/doxygen/functions_s.html
index 0fb012def6..6534f1d7d0 100644
--- a/docs/reference/api/doxygen/functions_s.html
+++ b/docs/reference/api/doxygen/functions_s.html
@@ -447,6 +447,9 @@ $(function() {
<li>set_num_inputs()
: <a class="el" href="classtvm_1_1OpRegEntry.html#af3bbb881b17dcc8c19ddb8ec9b40e462">tvm::OpRegEntry</a>
</li>
+<li>set_outputs_enabled_
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>set_repr_bytes()
: <a class="el" href="classtvm_1_1ReflectionVTable_1_1Registry.html#a27f62397ab10a8468c7de8350a6d1cee">tvm::ReflectionVTable::Registry</a>
</li>
@@ -501,6 +504,12 @@ $(function() {
<li>SetOneInput()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ab66c1484cfb630914dd41da36ab91db1">tvm::runtime::vm::VirtualMachine</a>
</li>
+<li>SetOutputs()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a2ee3a67f145ed44cabfb4d456c048445">tvm::runtime::vm::VirtualMachine</a>
+</li>
+<li>SetOutputTensorsToRegister()
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a95a0552177a93f4839ab431756efeaf3">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>SetScope()
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#aa4760135d373af488a08aaeba7114c48">tvm::tir::ScheduleNode</a>
</li>
@@ -779,7 +788,7 @@ $(function() {
: <a class="el" href="structtvm_1_1relay_1_1MultiBoxPriorAttrs.html#ad6d089344fa741021584222ffa70a451">tvm::relay::MultiBoxPriorAttrs</a>
</li>
<li>SizeVar()
-: <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#ac470249315d9e395ad581d35dd5dcb05">tvm::tir::SizeVar</a>
+: <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#a0f8cb8a92feb96343939d223db90f7cd">tvm::tir::SizeVar</a>
</li>
<li>Slice()
: <a class="el" href="classtvm_1_1te_1_1Tensor_1_1Slice.html#ab314819e8bcca6421e9a4f33e48578c3">tvm::te::Tensor::Slice</a>
@@ -824,7 +833,7 @@ $(function() {
: <a class="el" href="classtvm_1_1script_1_1printer_1_1DocNode.html#a29e21c8f39639d1d30697971267847a8">tvm::script::printer::DocNode</a>
</li>
<li>SourceMap()
-: <a class="el" href="classtvm_1_1parser_1_1SourceMap.html#afc48463cc0967ab79876178613a5aff2">tvm::parser::SourceMap</a>
+: <a class="el" href="classtvm_1_1parser_1_1SourceMap.html#a43518e78ad2060e9400d893078c48008">tvm::parser::SourceMap</a>
</li>
<li>space_generator
: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a7bdfdd48530bfe380c5f6c143158a07f">tvm::meta_schedule::TuneContextNode</a>
@@ -888,7 +897,7 @@ $(function() {
: <a class="el" href="classtvm_1_1te_1_1Stage.html#a51432f38d9ec4792a2525023179ae604">tvm::te::Stage</a>
</li>
<li>SplitStep()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1SplitStep.html#a64ed86582a56a2645b3e4eb44ecb31af">tvm::auto_scheduler::SplitStep</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1SplitStep.html#a184575a8029d77f7a3bee23d81141df5">tvm::auto_scheduler::SplitStep</a>
</li>
<li>src
: <a class="el" href="classtvm_1_1arith_1_1IntConstraintsTransformNode.html#a8ce159fc6db748e5092fa937de3fde53">tvm::arith::IntConstraintsTransformNode</a>
@@ -919,8 +928,8 @@ $(function() {
: <a class="el" href="structtvm_1_1relay_1_1DeviceCopyAttrs.html#aac5b2c76325a587bbefaa5af87b4138f">tvm::relay::DeviceCopyAttrs</a>
</li>
<li>Stage()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1Stage.html#af0643fe8c1298451c9a322f915c48843">tvm::auto_scheduler::Stage</a>
-, <a class="el" href="classtvm_1_1te_1_1Stage.html#afec82602b9321c489b88632a005335f8">tvm::te::Stage</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1Stage.html#a39ffbb1b4e189180bc4067e74965f42b">tvm::auto_scheduler::Stage</a>
+, <a class="el" href="classtvm_1_1te_1_1Stage.html#a1ecdc9a000be62c9cc26a96d4c33e36e">tvm::te::Stage</a>
</li>
<li>stage_id
: <a class="el" href="classtvm_1_1auto__scheduler_1_1StepNode.html#afcc7aaf263348f66139307affbfcee09">tvm::auto_scheduler::StepNode</a>
@@ -1003,7 +1012,7 @@ $(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#a79e21b14d3ab57209577bf4a8f694a87">tvm::tir::StmtNode</a>
+: <a class="el" href="classtvm_1_1tir_1_1StmtNode.html#a67693c4e97ae49890ea74605fe1b1f74">tvm::tir::StmtNode</a>
</li>
<li>stmts
: <a class="el" href="classtvm_1_1script_1_1ir__builder_1_1tir_1_1TIRFrameNode.html#a13776bb5c2e5403138fbee06d4fdad40">tvm::script::ir_builder::tir::TIRFrameNode</a>
diff --git a/docs/reference/api/doxygen/functions_t.html b/docs/reference/api/doxygen/functions_t.html
index 40bae37c72..6802685eae 100644
--- a/docs/reference/api/doxygen/functions_t.html
+++ b/docs/reference/api/doxygen/functions_t.html
@@ -81,7 +81,7 @@ $(function() {
, <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a46879dbe84105fb621a6167f8d73b223">tvm::runtime::vm::Instruction</a>
</li>
<li>Target()
-: <a class="el" href="classtvm_1_1Target.html#a77f3d7cc97d8cfd7172af58b4e784d89">tvm::Target</a>
+: <a class="el" href="classtvm_1_1Target.html#a58a5a1e042e265fe5a6973045226fe1a">tvm::Target</a>
</li>
<li>target
: <a class="el" href="classtvm_1_1VirtualDeviceNode.html#a8b2d427d9e21886ccaeaae5e9cc55aaf">tvm::VirtualDeviceNode</a>
@@ -1474,7 +1474,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a0d72a6fa7263821c14bcd37837998ed9">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#a6b346a6d0b601eff5a100c7a207e9c86">tvm::runtime::TypedPackedFunc< R(Args...)></a>
</li>
<li>TypeIndex2Key()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
@@ -1497,7 +1497,7 @@ $(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>types
: <a class="el" href="classtvm_1_1TupleAffineTypeNode.html#a30c834b7e1cb64467e6587ac16ebb187">tvm::TupleAffineTypeNode</a>
diff --git a/docs/reference/api/doxygen/functions_v.html b/docs/reference/api/doxygen/functions_v.html
index 73266e3069..3e7fd52abc 100644
--- a/docs/reference/api/doxygen/functions_v.html
+++ b/docs/reference/api/doxygen/functions_v.html
@@ -630,7 +630,7 @@ $(function() {
</li>
<li>VisitStmt_()
: <a class="el" href="classtvm_1_1tir_1_1StmtFunctor_3_01R_07const_01Stmt_01_6n_00_01Args_8_8_8_01args_08_4.html#ab10dd3ea7414d0c6c415857be5b5ad7b">tvm::tir::StmtFunctor< R(const Stmt &n, Args... args)></a>
-, <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#abea492fd2fee9442cc1995f46ef7fd60">tvm::tir::StmtMutator</a>
+, <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a971adb4c88808a67317da73954e093b5">tvm::tir::StmtMutator</a>
, <a class="el" href="classtvm_1_1tir_1_1StmtVisitor.html#a4794fa6c9c4f893ad68d5930b1334c97">tvm::tir::StmtVisitor</a>
</li>
<li>VisitStmtDefault_()
@@ -645,9 +645,9 @@ $(function() {
, <a class="el" href="classtvm_1_1TypeMutator.html#a84e824911927d98e20a338eab8b75a45">tvm::TypeMutator</a>
</li>
<li>VisitType_()
-: <a class="el" href="classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html#a9f728a703d68743e8b305acb68e5eb87">tvm::TypeFunctor< R(const Type &n, Args...)></a>
-, <a class="el" href="classtvm_1_1TypeMutator.html#ab270cb7a0d9af50362137c1d68d32276">tvm::TypeMutator</a>
-, <a class="el" href="classtvm_1_1TypeVisitor.html#adb2f5c5f8e3fbe5b62ce8527cd59a30b">tvm::TypeVisitor</a>
+: <a class="el" href="classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html#a0e715c54558934e4504c366ff803d8e1">tvm::TypeFunctor< R(const Type &n, Args...)></a>
+, <a class="el" href="classtvm_1_1TypeMutator.html#a2a78bda75555650a37a80e1e074d562a">tvm::TypeMutator</a>
+, <a class="el" href="classtvm_1_1TypeVisitor.html#af92188034706eec6c1ce5c8240f65cc0">tvm::TypeVisitor</a>
</li>
<li>VisitTypeDefault_()
: <a class="el" href="classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html#a91553f9e04c39b3821a70ae4f7b0c597">tvm::TypeFunctor< R(const Type &n, Args...)></a>
@@ -669,7 +669,7 @@ $(function() {
: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html#a8f8c990ee4fa7cb7472f5440f2ca3bde">tvm::runtime::vm::VMFrame</a>
</li>
<li>VMFunction()
-: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#af9d2bdcf19642c21bc4909b9e9b6196d">tvm::runtime::vm::VMFunction</a>
+: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#aea763069fe1dd6849ce0d1ec336931e0">tvm::runtime::vm::VMFunction</a>
</li>
<li>Void()
: <a class="el" href="classtvm_1_1runtime_1_1DataType.html#ab8dc0832aff8fd7421884c0fe20a3bfd">tvm::runtime::DataType</a>
diff --git a/docs/reference/api/doxygen/functions_vars_o.html b/docs/reference/api/doxygen/functions_vars_o.html
index 575c36665a..55e1394ebc 100644
--- a/docs/reference/api/doxygen/functions_vars_o.html
+++ b/docs/reference/api/doxygen/functions_vars_o.html
@@ -202,12 +202,18 @@ $(function() {
, <a class="el" href="structtvm_1_1relay_1_1AdaptivePool3DAttrs.html#a0c56cb9665840dcc8e949c41d39c710d">tvm::relay::AdaptivePool3DAttrs</a>
, <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a6bb6a1b8be0c078394f2336970aab1af">tvm::runtime::vm::Instruction</a>
</li>
+<li>output_tensor_reg_indices_
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa98e90db9a3ef70c732b5322171023c2">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>outputs
: <a class="el" href="classtvm_1_1te_1_1HybridOpNode.html#a6ff8e6faa8d01063e32a2c124721df29">tvm::te::HybridOpNode</a>
, <a class="el" href="classtvm_1_1te_1_1ScheduleNode.html#a27b0f687f7b20fcc6416a49e041712d8">tvm::te::ScheduleNode</a>
, <a class="el" href="classtvm_1_1tir_1_1InstructionNode.html#a745f994b096890961ed67b17f2040bba">tvm::tir::InstructionNode</a>
, <a class="el" href="structTVMMetadata.html#ae98ddb5d3a598ab923d8cadc66d38632">TVMMetadata</a>
</li>
+<li>outputs_
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a43d9a2e6056305a8c14941eb08f2cf29">tvm::runtime::vm::VirtualMachine</a>
+</li>
</ul>
</div><!-- contents -->
<!-- start footer part -->
diff --git a/docs/reference/api/doxygen/functions_vars_p.html b/docs/reference/api/doxygen/functions_vars_p.html
index c7bb73e21a..250b328857 100644
--- a/docs/reference/api/doxygen/functions_vars_p.html
+++ b/docs/reference/api/doxygen/functions_vars_p.html
@@ -247,6 +247,9 @@ $(function() {
<li>preprocessor
: <a class="el" href="classtvm_1_1TargetKindNode.html#a47f02c66d0f972befdfb29ec592ecba0">tvm::TargetKindNode</a>
</li>
+<li>preresult_op_index_
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a37b4a705186bf76cb9aa5168dcbc3651">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>primitive_map
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html#ab5a31e8670a4f20564abc48610a90e8c">tvm::runtime::vm::Executable</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_vars_s.html b/docs/reference/api/doxygen/functions_vars_s.html
index b3bfad1db4..116596ee7f 100644
--- a/docs/reference/api/doxygen/functions_vars_s.html
+++ b/docs/reference/api/doxygen/functions_vars_s.html
@@ -152,6 +152,9 @@ $(function() {
<li>session_id
: <a class="el" href="structtvm_1_1runtime_1_1micro__rpc_1_1SessionHeader.html#ae3a24ea6c4a1569d540f1d5330bf73d5">tvm::runtime::micro_rpc::SessionHeader</a>
</li>
+<li>set_outputs_enabled_
+: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9">tvm::runtime::vm::VirtualMachine</a>
+</li>
<li>SetArgs
: <a class="el" href="structTVMPackedFunc.html#a455396ff85d8e8cff95e39ae15ad5cc6">TVMPackedFunc</a>
</li>
diff --git a/docs/reference/api/doxygen/runtime_2vm_2vm_8h_source.html b/docs/reference/api/doxygen/runtime_2vm_2vm_8h_source.html
index 4fae2aff40..e603daaa51 100644
--- a/docs/reference/api/doxygen/runtime_2vm_2vm_8h_source.html
+++ b/docs/reference/api/doxygen/runtime_2vm_2vm_8h_source.html
@@ -66,15 +66,16 @@ $(function() {
<div class="title">vm.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="runtime_2vm_2vm_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a7d46e436c01133647cd303719752f456"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a7d46e436c01133647cd303719752f456">tvm::runtime::vm::VirtualMachine::inputs_</a></div><div class="ttdeci">std::unordered_map< std::string, std::vector< ObjectRef > > inputs_</div><div class="ttdoc">The function name to inputs mapping. </div><div class="ttdef"><b>Definition:</b> vm.h:358</div></div>
+<a href="runtime_2vm_2vm_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a7d46e436c01133647cd303719752f456"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a7d46e436c01133647cd303719752f456">tvm::runtime::vm::VirtualMachine::inputs_</a></div><div class="ttdeci">std::unordered_map< std::string, std::vector< ObjectRef > > inputs_</div><div class="ttdoc">The function name to inputs mapping. </div><div class="ttdef"><b>Definition:</b> vm.h:439</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_aa98e90db9a3ef70c732b5322171023c2"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa98e90db9a3ef70c732b5322171023c2">tvm::runtime::vm::VirtualMachine::output_tensor_reg_indices_</a></div><div class="ttdeci">std::unordered_map< std::string, std::vector< Index > > output_tensor_reg_indices_</div><div class="ttdoc">The function name to indices of output tensors in register file. [...]
<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_1VirtualMachine_html_a50557c8e0398599341c1a8539c528860"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a50557c8e0398599341c1a8539c528860">tvm::runtime::vm::VirtualMachine::const_pool_</a></div><div class="ttdeci">std::vector< ObjectRef > const_pool_</div><div class="ttdoc">The constant pool for runtime. It caches the device dependent object to avoid rellocation of constant...</div><div class="ttdef"><b> [...]
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a50557c8e0398599341c1a8539c528860"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a50557c8e0398599341c1a8539c528860">tvm::runtime::vm::VirtualMachine::const_pool_</a></div><div class="ttdeci">std::vector< ObjectRef > const_pool_</div><div class="ttdoc">The constant pool for runtime. It caches the device dependent object to avoid rellocation of constant...</div><div class="ttdef"><b> [...]
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1VMFrame_html_a2f6c425a89ee6872ead9bc71ab87fdd1"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html#a2f6c425a89ee6872ead9bc71ab87fdd1">tvm::runtime::vm::VMFrame::caller_return_register</a></div><div class="ttdeci">RegName caller_return_register</div><div class="ttdoc">Register in caller&#39;s frame to put return value. </div><div class="ttdef"><b>Definition:</b> vm.h:126</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1VMFunction_html_ae2f6bf699f51fb33d1659d88ff6855e0"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#ae2f6bf699f51fb33d1659d88ff6855e0">tvm::runtime::vm::VMFunction::name</a></div><div class="ttdeci">std::string name</div><div class="ttdoc">The function&#39;s name. </div><div class="ttdef"><b>Definition:</b> vm.h:79</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="structtvm_1_1runtime_1_1vm_1_1VMFrame_html_a96a641c01ca63e6b146ef321319ec1f4"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html#a96a641c01ca63e6b146ef321319ec1f4">tvm::runtime::vm::VMFrame::func_index</a></div><div class="ttdeci">Index func_index</div><div class="ttdoc">The index into the function table, points to the caller. </div><div class="ttdef"><b>Definition:</b> vm.h:116</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_af9d51023b5d6451dac20d1a146ce5d38"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#af9d51023b5d6451dac20d1a146ce5d38">tvm::runtime::vm::VirtualMachine::func_index_</a></div><div class="ttdeci">Index func_index_</div><div class="ttdoc">The fuction table index of the current function. </div><div class="ttdef"><b>Definition:</b> vm.h:348</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_af9d51023b5d6451dac20d1a146ce5d38"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#af9d51023b5d6451dac20d1a146ce5d38">tvm::runtime::vm::VirtualMachine::func_index_</a></div><div class="ttdeci">Index func_index_</div><div class="ttdoc">The fuction table index of the current function. </div><div class="ttdef"><b>Definition:</b> vm.h:429</div></div>
<div class="ttc" id="namespacestd_html"><div class="ttname"><a href="namespacestd.html">std</a></div><div class="ttdef"><b>Definition:</b> loop_state.h:456</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_1_1vm_html_a8d8d95ce8d629c7213f2f595917870eca97ad0208b167666da31720813abe1174"><div class="ttname"><a href="namespacetvm_1_1runtime_1_1vm.html#a8d8d95ce8d629c7213f2f595917870eca97ad0208b167666da31720813abe1174">tvm::runtime::vm::Opcode::InvokePacked</a></div></div>
<div class="ttc" id="namespacetvm_1_1runtime_1_1vm_html_a8d8d95ce8d629c7213f2f595917870ecab9376e9e3c4d48f5e35a3f355ae1f74a"><div class="ttname"><a href="namespacetvm_1_1runtime_1_1vm.html#a8d8d95ce8d629c7213f2f595917870ecab9376e9e3c4d48f5e35a3f355ae1f74a">tvm::runtime::vm::Opcode::Invoke</a></div></div>
@@ -82,17 +83,17 @@ $(function() {
<div class="ttc" id="closure_8h_html"><div class="ttname"><a href="closure_8h.html">closure.h</a></div><div class="ttdoc">Runtime Closure container types. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Closure_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Closure.html">tvm::runtime::Closure</a></div><div class="ttdoc">reference to closure. </div><div class="ttdef"><b>Definition:</b> closure.h:44</div></div>
<div class="ttc" id="memory__manager_8h_html"><div class="ttname"><a href="memory__manager_8h.html">memory_manager.h</a></div><div class="ttdoc">Abstract device memory management API. </div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a619aa7ba254da546fb5beadb9749f674"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a619aa7ba254da546fb5beadb9749f674">tvm::runtime::vm::VirtualMachine::exec_</a></div><div class="ttdeci">ObjectPtr< Executable > exec_</div><div class="ttdoc">The executable the VM will operate on. </div><div class="ttdef"><b>Definition:</b> vm.h:356</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a619aa7ba254da546fb5beadb9749f674"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a619aa7ba254da546fb5beadb9749f674">tvm::runtime::vm::VirtualMachine::exec_</a></div><div class="ttdeci">ObjectPtr< Executable > exec_</div><div class="ttdoc">The executable the VM will operate on. </div><div class="ttdef"><b>Definition:</b> vm.h:437</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a00f035566a720dbac56f5dea042fb0ec"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a00f035566a720dbac56f5dea042fb0ec">tvm::runtime::vm::VirtualMachine::type_key</a></div><div class="ttdeci">const char * type_key() const final</div><div class="ttdef"><b>Definition:</b> vm.h:171</div></div>
<div class="ttc" id="executable_8h_html"><div class="ttname"><a href="executable_8h.html">executable.h</a></div><div class="ttdoc">The Relay virtual machine executable. </div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a602daa8d70ae598a833d8601d1ef6d95"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a602daa8d70ae598a833d8601d1ef6d95">tvm::runtime::vm::VirtualMachine::devices_</a></div><div class="ttdeci">std::vector< Device > devices_</div><div class="ttdoc">The "physical" devices the VM can execute primitives on. All "device indexes" are w...</div><div class="ttdef"><b>Definit [...]
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a602daa8d70ae598a833d8601d1ef6d95"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a602daa8d70ae598a833d8601d1ef6d95">tvm::runtime::vm::VirtualMachine::devices_</a></div><div class="ttdeci">std::vector< Device > devices_</div><div class="ttdoc">The "physical" devices the VM can execute primitives on. All "device indexes" are w...</div><div class="ttdef"><b>Definit [...]
<div class="ttc" id="classtvm_1_1runtime_1_1TVMArgs_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMArgs.html">tvm::runtime::TVMArgs</a></div><div class="ttdoc">Arguments into TVM functions. </div><div class="ttdef"><b>Definition:</b> packed_func.h:391</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1VMFrame_html_a583dcf6c0ed3f3d2916679382c7a0775"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html#a583dcf6c0ed3f3d2916679382c7a0775">tvm::runtime::vm::VMFrame::register_file</a></div><div class="ttdeci">std::vector< ObjectRef > register_file</div><div class="ttdoc">Statically allocated space for objects. </div><div class="ttdef"><b>Definition:</b> vm.h:123</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1VMFunction_html_aea763069fe1dd6849ce0d1ec336931e0"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#aea763069fe1dd6849ce0d1ec336931e0">tvm::runtime::vm::VMFunction::VMFunction</a></div><div class="ttdeci">VMFunction(std::string name, std::vector< std::string > params, std::vector< Instruction > instructions, Index register_file_size, std::vector< Index > param_device_indexes)</div><div class="t [...]
<div class="ttc" id="namespacetvm_1_1runtime_1_1vm_html_a3bbbf700719e9dc3dda2bc25210c18ae"><div class="ttname"><a href="namespacetvm_1_1runtime_1_1vm.html#a3bbbf700719e9dc3dda2bc25210c18ae">tvm::runtime::vm::RegName</a></div><div class="ttdeci">int64_t RegName</div><div class="ttdoc">A register name. </div><div class="ttdef"><b>Definition:</b> bytecode.h:38</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_1VirtualMachine_html_ae2e5377a5dbf7335ed8989512457a2f5"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ae2e5377a5dbf7335ed8989512457a2f5">tvm::runtime::vm::VirtualMachine::packed_funcs_</a></div><div class="ttdeci">std::vector< PackedFunc > packed_funcs_</div><div class="ttdoc">The virtual machine&#39;s packed function table. </div><div class="ttdef"><b>Definition:</b> vm.h:344</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a0ef00d527a1c03221030c5fec2ad519d"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a0ef00d527a1c03221030c5fec2ad519d">tvm::runtime::vm::VirtualMachine::allocators_</a></div><div class="ttdeci">std::vector< Allocator * > allocators_</div><div class="ttdoc">The cached memory allocators, one per device. </div><div class="ttdef"><b>Definition:</b> vm.h:366</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_ae2e5377a5dbf7335ed8989512457a2f5"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ae2e5377a5dbf7335ed8989512457a2f5">tvm::runtime::vm::VirtualMachine::packed_funcs_</a></div><div class="ttdeci">std::vector< PackedFunc > packed_funcs_</div><div class="ttdoc">The virtual machine&#39;s packed function table. </div><div class="ttdef"><b>Definition:</b> vm.h:425</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a0ef00d527a1c03221030c5fec2ad519d"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a0ef00d527a1c03221030c5fec2ad519d">tvm::runtime::vm::VirtualMachine::allocators_</a></div><div class="ttdeci">std::vector< Allocator * > allocators_</div><div class="ttdoc">The cached memory allocators, one per device. </div><div class="ttdef"><b>Definition:</b> vm.h:455</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1VMFunction_html_a046985e3f5a2b4201298555514d5d356"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#a046985e3f5a2b4201298555514d5d356">tvm::runtime::vm::VMFunction::instructions</a></div><div class="ttdeci">std::vector< Instruction > instructions</div><div class="ttdoc">The instructions representing the function. </div><div class="ttdef"><b>Definition:</b> vm.h:83</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VMClosureObj_html_af252588d00a4e0b7086edcea4cdfae6f"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VMClosureObj.html#af252588d00a4e0b7086edcea4cdfae6f">tvm::runtime::vm::VMClosureObj::func_index</a></div><div class="ttdeci">size_t func_index</div><div class="ttdoc">The index into the function list. The function could be any function object that is compatible to the...</div><div class="ttdef"><b>Definition:</b> vm.h:55</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
@@ -106,19 +107,21 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VMClosureObj_html_ab9d8ce9e837254a7224e0aab221e0de5"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VMClosureObj.html#ab9d8ce9e837254a7224e0aab221e0de5">tvm::runtime::vm::VMClosureObj::_type_index</a></div><div class="ttdeci">static constexpr const uint32_t _type_index</div><div class="ttdef"><b>Definition:</b> vm.h:59</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="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a4a268dec17fdd0942fe7dce78974783f"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a4a268dec17fdd0942fe7dce78974783f">tvm::runtime::vm::VirtualMachine::frames_</a></div><div class="ttdeci">std::vector< VMFrame > frames_</div><div class="ttdoc">The current stack of call frames. </div><div class="ttdef"><b>Definition:</b> vm.h:346</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a4a268dec17fdd0942fe7dce78974783f"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a4a268dec17fdd0942fe7dce78974783f">tvm::runtime::vm::VirtualMachine::frames_</a></div><div class="ttdeci">std::vector< VMFrame > frames_</div><div class="ttdoc">The current stack of call frames. </div><div class="ttdef"><b>Definition:</b> vm.h:427</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VMClosureObj_html_aedda640042860f3347846735822bb464"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VMClosureObj.html#aedda640042860f3347846735822bb464">tvm::runtime::vm::VMClosureObj::TVM_DECLARE_FINAL_OBJECT_INFO</a></div><div class="ttdeci">TVM_DECLARE_FINAL_OBJECT_INFO(VMClosureObj, ClosureObj)</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a6edbbbb71000617f644232de37d53338"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6edbbbb71000617f644232de37d53338">tvm::runtime::vm::VirtualMachine::VirtualMachine</a></div><div class="ttdeci">VirtualMachine()</div><div class="ttdef"><b>Definition:</b> vm.h:173</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ClosureObj_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ClosureObj.html">tvm::runtime::ClosureObj</a></div><div class="ttdoc">An object representing a closure. This object is used by both the Relay VM and interpreter. </div><div class="ttdef"><b>Definition:</b> closure.h:36</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="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a583f4afb3292882df571a4fdf3cbf947"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a583f4afb3292882df571a4fdf3cbf947">tvm::runtime::vm::VirtualMachine::pc_</a></div><div class="ttdeci">Index pc_</div><div class="ttdoc">The virtual machine PC. </div><div class="ttdef"><b>Definition:</b> vm.h:352</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a583f4afb3292882df571a4fdf3cbf947"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a583f4afb3292882df571a4fdf3cbf947">tvm::runtime::vm::VirtualMachine::pc_</a></div><div class="ttdeci">Index pc_</div><div class="ttdoc">The virtual machine PC. </div><div class="ttdef"><b>Definition:</b> vm.h:433</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a62dead74c40c1a6ac03aec56918d98c7"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a62dead74c40c1a6ac03aec56918d98c7">tvm::runtime::vm::VirtualMachine::~VirtualMachine</a></div><div class="ttdeci">virtual ~VirtualMachine()</div><div class="ttdef"><b>Definition:</b> vm.h:169</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a6a3eb3eb9362ee6567e9ee6a6bc7ccf9"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9">tvm::runtime::vm::VirtualMachine::set_outputs_enabled_</a></div><div class="ttdeci">std::unordered_map< std::string, bool > set_outputs_enabled_</div><div class="ttdoc">The function name to flag enabling scenario with set outputs. </div><div class="ttdef"><b>Definitio [...]
<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="structtvm_1_1runtime_1_1vm_1_1VMFrame_html_a189d59efcb86fa14dc486c2852a5f01b"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html#a189d59efcb86fa14dc486c2852a5f01b">tvm::runtime::vm::VMFrame::args</a></div><div class="ttdeci">Index args</div><div class="ttdoc">The number of arguments. </div><div class="ttdef"><b>Definition:</b> vm.h:118</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMArgValue_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMArgValue.html">tvm::runtime::TVMArgValue</a></div><div class="ttdoc">A single argument value to PackedFunc. Containing both type_code and TVMValue. </div><div class="ttdef"><b>Definition:</b> packed_func.h:646</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1PackedFunc_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1PackedFunc.html">tvm::runtime::PackedFunc</a></div><div class="ttdoc">Packed function is a type-erased function. The arguments are passed by packed format. </div><div class="ttdef"><b>Definition:</b> packed_func.h:138</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_ab220bfa34c9abb2935c3b622d9bc03b2"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ab220bfa34c9abb2935c3b622d9bc03b2">tvm::runtime::vm::VirtualMachine::code_</a></div><div class="ttdeci">const Instruction * code_</div><div class="ttdoc">The current pointer to the code section. </div><div class="ttdef"><b>Definition:</b> vm.h:350</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_afd0505002da7e7f86f82b2f3325ff127"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#afd0505002da7e7f86f82b2f3325ff127">tvm::runtime::vm::VirtualMachine::return_register_</a></div><div class="ttdeci">ObjectRef return_register_</div><div class="ttdoc">The special return register. </div><div class="ttdef"><b>Definition:</b> vm.h:354</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_a43d9a2e6056305a8c14941eb08f2cf29"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a43d9a2e6056305a8c14941eb08f2cf29">tvm::runtime::vm::VirtualMachine::outputs_</a></div><div class="ttdeci">std::unordered_map< std::string, std::vector< ObjectRef > > outputs_</div><div class="ttdoc">The function name to pre-allocated outputs mapping. </div><div class="ttdef"><b>Definition:</b> v [...]
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_ab220bfa34c9abb2935c3b622d9bc03b2"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ab220bfa34c9abb2935c3b622d9bc03b2">tvm::runtime::vm::VirtualMachine::code_</a></div><div class="ttdeci">const Instruction * code_</div><div class="ttdoc">The current pointer to the code section. </div><div class="ttdef"><b>Definition:</b> vm.h:431</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1VirtualMachine_html_afd0505002da7e7f86f82b2f3325ff127"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#afd0505002da7e7f86f82b2f3325ff127">tvm::runtime::vm::VirtualMachine::return_register_</a></div><div class="ttdeci">ObjectRef return_register_</div><div class="ttdoc">The special return register. </div><div class="ttdef"><b>Definition:</b> vm.h:435</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1Allocator_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1Allocator.html">tvm::runtime::vm::Allocator</a></div><div class="ttdef"><b>Definition:</b> memory_manager.h:55</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1VMFrame_html_a8f8c990ee4fa7cb7472f5440f2ca3bde"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html#a8f8c990ee4fa7cb7472f5440f2ca3bde">tvm::runtime::vm::VMFrame::VMFrame</a></div><div class="ttdeci">VMFrame(Index pc, Index func_index, Index args, const Instruction *code, Index register_file_size)</div><div class="ttdef"><b>Definition:</b> vm.h:128</div></div>
<div class="ttc" id="namespacetvm_1_1script_1_1ir__builder_1_1tir_html_abd98d9f9b1651dfb649d590adf9335cd"><div class="ttname"><a href="namespacetvm_1_1script_1_1ir__builder_1_1tir.html#abd98d9f9b1651dfb649d590adf9335cd">tvm::script::ir_builder::tir::Init</a></div><div class="ttdeci">BlockInitFrame Init()</div><div class="ttdoc">The block initialization statement. </div></div>
diff --git a/docs/reference/api/doxygen/search/all_10.js b/docs/reference/api/doxygen/search/all_10.js
index 9f314d8584..9ce5090c6f 100644
--- a/docs/reference/api/doxygen/search/all_10.js
+++ b/docs/reference/api/doxygen/search/all_10.js
@@ -163,5 +163,7 @@ var searchData=
['output_5fplaceholders',['output_placeholders',['../classtvm_1_1te_1_1ExternOpNode.html#a004d2ec4a439339a2067e4fe7b93dac8',1,'tvm::te::ExternOpNode']]],
['output_5fshape',['output_shape',['../structtvm_1_1relay_1_1SparseToDenseAttrs.html#a96725ff7c8a481e81a2fd0ad163b4ecf',1,'tvm::relay::SparseToDenseAttrs::output_shape()'],['../classtvm_1_1te_1_1OperationNode.html#a7c4fc476de1543ea65c83e02631bfd09',1,'tvm::te::OperationNode::output_shape()'],['../classtvm_1_1te_1_1PlaceholderOpNode.html#a22624cba74f79b3fa5a6ac2a4b986c79',1,'tvm::te::PlaceholderOpNode::output_shape()'],['../classtvm_1_1te_1_1BaseComputeOpNode.html#acdd22cc7c737d4dc8b6bf [...]
['output_5fsize',['output_size',['../structtvm_1_1relay_1_1AdaptivePool1DAttrs.html#a18b0e1c79c534fec9eabb0656a395c9e',1,'tvm::relay::AdaptivePool1DAttrs::output_size()'],['../structtvm_1_1relay_1_1AdaptivePool2DAttrs.html#a545f40ec0dbdf52f628bebcc23a63950',1,'tvm::relay::AdaptivePool2DAttrs::output_size()'],['../structtvm_1_1relay_1_1AdaptivePool3DAttrs.html#a0c56cb9665840dcc8e949c41d39c710d',1,'tvm::relay::AdaptivePool3DAttrs::output_size()'],['../structtvm_1_1runtime_1_1vm_1_1Instru [...]
- ['outputs',['outputs',['../structTVMMetadata.html#ae98ddb5d3a598ab923d8cadc66d38632',1,'TVMMetadata::outputs()'],['../classtvm_1_1te_1_1HybridOpNode.html#a6ff8e6faa8d01063e32a2c124721df29',1,'tvm::te::HybridOpNode::outputs()'],['../classtvm_1_1te_1_1ScheduleNode.html#a27b0f687f7b20fcc6416a49e041712d8',1,'tvm::te::ScheduleNode::outputs()'],['../classtvm_1_1tir_1_1InstructionNode.html#a745f994b096890961ed67b17f2040bba',1,'tvm::tir::InstructionNode::outputs()'],['../classtvm_1_1runtime_1_ [...]
+ ['output_5ftensor_5freg_5findices_5f',['output_tensor_reg_indices_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa98e90db9a3ef70c732b5322171023c2',1,'tvm::runtime::vm::VirtualMachine']]],
+ ['outputs',['outputs',['../structTVMMetadata.html#ae98ddb5d3a598ab923d8cadc66d38632',1,'TVMMetadata::outputs()'],['../classtvm_1_1te_1_1HybridOpNode.html#a6ff8e6faa8d01063e32a2c124721df29',1,'tvm::te::HybridOpNode::outputs()'],['../classtvm_1_1te_1_1ScheduleNode.html#a27b0f687f7b20fcc6416a49e041712d8',1,'tvm::te::ScheduleNode::outputs()'],['../classtvm_1_1tir_1_1InstructionNode.html#a745f994b096890961ed67b17f2040bba',1,'tvm::tir::InstructionNode::outputs()'],['../classtvm_1_1runtime_1_ [...]
+ ['outputs_5f',['outputs_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a43d9a2e6056305a8c14941eb08f2cf29',1,'tvm::runtime::vm::VirtualMachine']]]
];
diff --git a/docs/reference/api/doxygen/search/all_11.js b/docs/reference/api/doxygen/search/all_11.js
index 39132c0ccd..66f881f8fd 100644
--- a/docs/reference/api/doxygen/search/all_11.js
+++ b/docs/reference/api/doxygen/search/all_11.js
@@ -35,7 +35,7 @@ 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_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()'],['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#af443e6c0816e4e4ff97881df7a11a6db',1,'tvm::script::ir_builder::tir: [...]
+ ['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()'],['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#af443e6c0816e4e4ff97881df7a11a6db',1,'tvm::script::ir_builder::tir: [...]
['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']]],
@@ -67,7 +67,7 @@ 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_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',['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_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']]],
@@ -181,6 +181,7 @@ var searchData=
['prepare_5fhwio',['prepare_hwio',['../namespacetvm_1_1runtime_1_1hexagon.html#a4bf7e818d926bb0f612cb35310258693',1,'tvm::runtime::hexagon']]],
['prepare_5fnhwc',['prepare_nhwc',['../namespacetvm_1_1runtime_1_1hexagon.html#a37822d9bcefcf7b5be93ffa6a10991d9',1,'tvm::runtime::hexagon']]],
['preprocessor',['preprocessor',['../classtvm_1_1TargetKindNode.html#a47f02c66d0f972befdfb29ec592ecba0',1,'tvm::TargetKindNode']]],
+ ['preresult_5fop_5findex_5f',['preresult_op_index_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a37b4a705186bf76cb9aa5168dcbc3651',1,'tvm::runtime::vm::VirtualMachine']]],
['prettyprint',['PrettyPrint',['../namespacetvm.html#a60c4359254ce7ac364bb97a8bfc13803',1,'tvm']]],
['pretuning',['PreTuning',['../classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#ad88e1545e88dc1934c25f4b417077aff',1,'tvm::meta_schedule::SearchStrategyNode::PreTuning()'],['../classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a53127523582ffdb12f40c9433a577adf',1,'tvm::meta_schedule::PySearchStrategyNode::PreTuning()']]],
['primexpr',['PrimExpr',['../classtvm_1_1PrimExpr.html',1,'tvm::PrimExpr'],['../classtvm_1_1PrimExpr.html#a7f0ca30e951608a0b36a77a66d4d19e0',1,'tvm::PrimExpr::PrimExpr(int32_t value)'],['../classtvm_1_1PrimExpr.html#a756d3f8b17b019560946524951ae6118',1,'tvm::PrimExpr::PrimExpr(float value)']]],
@@ -199,6 +200,7 @@ var searchData=
['printdocstring',['PrintDocString',['../classtvm_1_1BaseAttrsNode.html#a80929190102473038bce5b4f6c42dff6',1,'tvm::BaseAttrsNode']]],
['printer_2eh',['printer.h',['../printer_8h.html',1,'']]],
['printindent',['PrintIndent',['../classtvm_1_1ReprPrinter.html#a9c5941e7c4e24c9880dbd340cc226bf4',1,'tvm::ReprPrinter']]],
+ ['printinfoandsetinputargs',['PrintInfoAndSetInputArgs',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ac2ca0dc6162002d400e56ccc4c41fb9c',1,'tvm::runtime::vm::VirtualMachine']]],
['printir',['PrintIR',['../namespacetvm_1_1transform.html#a8cca5b98fb5d34e66444343786d85529',1,'tvm::transform']]],
['printstepsaspython',['PrintStepsAsPython',['../classtvm_1_1auto__scheduler_1_1ComputeDAG.html#ace0f0f385d5d3179dd5dc0a1f35990b4',1,'tvm::auto_scheduler::ComputeDAG']]],
['priority',['priority',['../classtvm_1_1auto__scheduler_1_1RPCRunnerNode.html#ad5c143b5ce09e135fb8c318d3c0042b9',1,'tvm::auto_scheduler::RPCRunnerNode']]],
diff --git a/docs/reference/api/doxygen/search/all_13.js b/docs/reference/api/doxygen/search/all_13.js
index 1bcebde449..6ab51c6cce 100644
--- a/docs/reference/api/doxygen/search/all_13.js
+++ b/docs/reference/api/doxygen/search/all_13.js
@@ -123,7 +123,7 @@ var searchData=
['rendererrors',['RenderErrors',['../classtvm_1_1ErrorReporter.html#a54699ec5f538bd207b5aa4e3f55181c6',1,'tvm::ErrorReporter']]],
['renewdefs',['RenewDefs',['../namespacetvm_1_1tir.html#a2e639c81d1c6875ead7764ab8a7cd553',1,'tvm::tir']]],
['renormalizesplitpattern',['RenormalizeSplitPattern',['../namespacetvm_1_1tir_1_1transform.html#a5c670c9efcd740f2f168b62e624c8c57',1,'tvm::tir::transform']]],
- ['reorder',['reorder',['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()']]],
+ ['reorder',['Reorder',['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()'],['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()']]],
['reorderstep',['ReorderStep',['../classtvm_1_1auto__scheduler_1_1ReorderStep.html',1,'tvm::auto_scheduler::ReorderStep'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a83b9dab5f38d5a4d42c6424ba437bc10',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(int stage_id, const Array< Integer > &after_ids)'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a9586534afef3e0f57ab31e8374e70792',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(dmlc::JSONReader *reader)']]],
['reorderstepnode',['ReorderStepNode',['../classtvm_1_1auto__scheduler_1_1ReorderStepNode.html',1,'tvm::auto_scheduler']]],
['reorg',['reorg',['../namespacetvm_1_1topi_1_1vision.html#a1014df582489005202c4218e51792314',1,'tvm::topi::vision']]],
@@ -163,7 +163,7 @@ var searchData=
['resize2dattrs',['Resize2DAttrs',['../structtvm_1_1relay_1_1Resize2DAttrs.html',1,'tvm::relay']]],
['resize3dattrs',['Resize3DAttrs',['../structtvm_1_1relay_1_1Resize3DAttrs.html',1,'tvm::relay']]],
['resolvedependency',['ResolveDependency',['../classtvm_1_1transform_1_1SequentialNode.html#a5549edf77e0a64bd6fcb692603967b8e',1,'tvm::transform::SequentialNode']]],
- ['result',['Result',['../classtvm_1_1meta__schedule_1_1RunnerFutureNode.html#a1b5438c21c436ce7a864487583fd32b2',1,'tvm::meta_schedule::RunnerFutureNode::Result()'],['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#ae0d33229af059c727db2abd3616660e0',1,'tvm::runtime::vm::Instruction::result()'],['../classtvm_1_1script_1_1ir__builder_1_1IRBuilderNode.html#ae9bab07b47a5fd7f27576cbcfddab953',1,'tvm::script::ir_builder::IRBuilderNode::result()'],['../classtvm_1_1tir_1_1CommReducerNode.html [...]
+ ['result',['result',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#ae0d33229af059c727db2abd3616660e0',1,'tvm::runtime::vm::Instruction::result()'],['../classtvm_1_1script_1_1ir__builder_1_1IRBuilderNode.html#ae9bab07b47a5fd7f27576cbcfddab953',1,'tvm::script::ir_builder::IRBuilderNode::result()'],['../classtvm_1_1tir_1_1CommReducerNode.html#a7030917568a088215da423fc56882814',1,'tvm::tir::CommReducerNode::result()'],['../classtvm_1_1meta__schedule_1_1RunnerFutureNode.html#a1b5438c21 [...]
['result_5f',['result_',['../classtvm_1_1detail_1_1AttrsSEqualVisitor.html#aeda3a91f0b2d1a7a9a075828954ff77f',1,'tvm::detail::AttrsSEqualVisitor']]],
['result_5ftype',['result_type',['../classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html#a24d4a3522ee6c4cdeed80dcdcc1424ad',1,'tvm::TypeFunctor< R(const Type &n, Args...)>::result_type()'],['../classtvm_1_1NodeFunctor_3_01R_07const_01ObjectRef_01_6n_00_01Args_8_8_8_08_4.html#ac7f687cb7dda02407b578a6683fa708a',1,'tvm::NodeFunctor< R(const ObjectRef &n, Args...)>::result_type()'],['../classtvm_1_1relay_1_1ExprFunctor_3_01R_07const_01Expr_01_6n [...]
['resulttype',['ResultType',['../structtvm_1_1runtime_1_1Array_1_1ValueConverter.html#a0db77cfd8032391d76dffc88eae8e09b',1,'tvm::runtime::Array::ValueConverter']]],
@@ -198,7 +198,7 @@ var searchData=
['rewritetensorize',['RewriteTensorize',['../classtvm_1_1meta__schedule_1_1Postproc.html#a95db036cfced4c2575367a26a41498ff',1,'tvm::meta_schedule::Postproc']]],
['rewriteunboundblock',['RewriteUnboundBlock',['../classtvm_1_1meta__schedule_1_1Postproc.html#a1836b2278bc24fdc227c490896d92980',1,'tvm::meta_schedule::Postproc']]],
['rewriteunsafeselect',['RewriteUnsafeSelect',['../namespacetvm_1_1tir_1_1transform.html#a4fe43327c4454dd05b6e925577443f49',1,'tvm::tir::transform']]],
- ['rfactor',['RFactor',['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()'],['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()']]],
+ ['rfactor',['rfactor',['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()']]],
['rfactorstep',['RfactorStep',['../classtvm_1_1auto__scheduler_1_1RfactorStep.html',1,'tvm::auto_scheduler::RfactorStep'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a26e6f85b55307f18fab4469e3bd4be0c',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(int stage_id, int iter_id, int factor_iter_id)'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a95575c21441177634178245ab562cb4f',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(dmlc::JSONReader *reader)']]],
['rfactorstepnode',['RfactorStepNode',['../classtvm_1_1auto__scheduler_1_1RfactorStepNode.html',1,'tvm::auto_scheduler']]],
['rhs',['rhs',['../classtvm_1_1relay_1_1ClauseNode.html#a93217eeea15c1f7c1a659da3da86d3bd',1,'tvm::relay::ClauseNode::rhs()'],['../classtvm_1_1script_1_1printer_1_1AssignDocNode.html#a436fcace00d445213fc367ece59c4067',1,'tvm::script::printer::AssignDocNode::rhs()'],['../classtvm_1_1script_1_1printer_1_1ForDocNode.html#aa72614136675287310ea08520f596642',1,'tvm::script::printer::ForDocNode::rhs()'],['../classtvm_1_1script_1_1printer_1_1ScopeDocNode.html#abf3636ac2820118a3d48f2fea32b2b0b' [...]
@@ -244,7 +244,7 @@ var searchData=
['runafterpass',['RunAfterPass',['../classtvm_1_1instrument_1_1PassInstrumentNode.html#a49332b9ab696afefa427b676dbaba1b0',1,'tvm::instrument::PassInstrumentNode']]],
['runbeforepass',['RunBeforePass',['../classtvm_1_1instrument_1_1PassInstrumentNode.html#a4c5781489ab0113fbfcb9a61e6348b43',1,'tvm::instrument::PassInstrumentNode']]],
['runcallbacks',['RunCallbacks',['../classtvm_1_1auto__scheduler_1_1SearchPolicyNode.html#a4bf8f2f816014b03ebea564d50afeba9',1,'tvm::auto_scheduler::SearchPolicyNode']]],
- ['runloop',['RunLoop',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ad83dfc94ba5e62875df9e780c750487b',1,'tvm::runtime::vm::VirtualMachine']]],
+ ['runloop',['RunLoop',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a08164ef76393a4efb002c1ea6b8ae447',1,'tvm::runtime::vm::VirtualMachine']]],
['runner',['Runner',['../classtvm_1_1meta__schedule_1_1Runner.html',1,'tvm::meta_schedule::Runner'],['../classtvm_1_1auto__scheduler_1_1TuningOptionsNode.html#a355d86b2c38f0827ae1b158753d1daa2',1,'tvm::auto_scheduler::TuningOptionsNode::runner()'],['../classtvm_1_1auto__scheduler_1_1ProgramMeasurerNode.html#a0f7a4a84637fd0309b52f61b65bee158',1,'tvm::auto_scheduler::ProgramMeasurerNode::runner()'],['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#a13c74317fb8dccd7fbdb728336b0950 [...]
['runner_2eh',['runner.h',['../runner_8h.html',1,'']]],
['runner_5ffutures',['runner_futures',['../classtvm_1_1meta__schedule_1_1TuneContextNode.html#a8b7bfb296b89ad8645fcf89bf645092a',1,'tvm::meta_schedule::TuneContextNode']]],
diff --git a/docs/reference/api/doxygen/search/all_14.js b/docs/reference/api/doxygen/search/all_14.js
index e35ce8649e..2a9bc4fef4 100644
--- a/docs/reference/api/doxygen/search/all_14.js
+++ b/docs/reference/api/doxygen/search/all_14.js
@@ -142,6 +142,7 @@ var searchData=
['set_5flower_5fbound',['set_lower_bound',['../structtvm_1_1detail_1_1AttrNopEntry.html#a36da34fc54009d63283d07e9d41657f7',1,'tvm::detail::AttrNopEntry::set_lower_bound()'],['../structtvm_1_1detail_1_1AttrInitEntry.html#a5608a2a457a397bf11f2be2776ec0653',1,'tvm::detail::AttrInitEntry::set_lower_bound()'],['../classtvm_1_1detail_1_1AttrDocEntry.html#a201e9d6c937d2f444d91fcc8185f8309',1,'tvm::detail::AttrDocEntry::set_lower_bound()'],['../structtvm_1_1detail_1_1AttrTriggerNonDefaultEntry [...]
['set_5fname',['set_name',['../classtvm_1_1OpRegEntry.html#a655190541a44ee287902ae1fead3ff94',1,'tvm::OpRegEntry::set_name()'],['../classtvm_1_1TargetTagRegEntry.html#a2bf53ad591587d2b3f710d01a0b6d5bb',1,'tvm::TargetTagRegEntry::set_name()'],['../classtvm_1_1TargetKindRegEntry.html#a36f21402bccb03300478d6c85bd05512',1,'tvm::TargetKindRegEntry::set_name()'],['../classtvm_1_1tir_1_1InstructionKindRegEntry.html#ac2c87342f8a017e55474e0094561f79c',1,'tvm::tir::InstructionKindRegEntry::set_n [...]
['set_5fnum_5finputs',['set_num_inputs',['../classtvm_1_1OpRegEntry.html#af3bbb881b17dcc8c19ddb8ec9b40e462',1,'tvm::OpRegEntry']]],
+ ['set_5foutputs_5fenabled_5f',['set_outputs_enabled_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9',1,'tvm::runtime::vm::VirtualMachine']]],
['set_5frepr_5fbytes',['set_repr_bytes',['../classtvm_1_1ReflectionVTable_1_1Registry.html#a27f62397ab10a8468c7de8350a6d1cee',1,'tvm::ReflectionVTable::Registry']]],
['set_5fscope',['set_scope',['../classtvm_1_1te_1_1Stage.html#a0dc42f190125f0cf63e8d749ae66af7c',1,'tvm::te::Stage']]],
['set_5fstore_5fpredicate',['set_store_predicate',['../classtvm_1_1te_1_1Stage.html#a0056636228aed23f71eecc0810731436',1,'tvm::te::Stage']]],
@@ -162,6 +163,8 @@ var searchData=
['setmaxconcurrency',['SetMaxConcurrency',['../namespacetvm_1_1runtime_1_1threading.html#ad66f7fc304b915bebdcfc5c7004016c7',1,'tvm::runtime::threading']]],
['setobject',['SetObject',['../classtvm_1_1runtime_1_1TVMArgsSetter.html#adfc052b0786ef1296d29e0b87f71a03e',1,'tvm::runtime::TVMArgsSetter']]],
['setoneinput',['SetOneInput',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ab66c1484cfb630914dd41da36ab91db1',1,'tvm::runtime::vm::VirtualMachine']]],
+ ['setoutputs',['SetOutputs',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a2ee3a67f145ed44cabfb4d456c048445',1,'tvm::runtime::vm::VirtualMachine']]],
+ ['setoutputtensorstoregister',['SetOutputTensorsToRegister',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a95a0552177a93f4839ab431756efeaf3',1,'tvm::runtime::vm::VirtualMachine']]],
['setscope',['SetScope',['../classtvm_1_1tir_1_1ScheduleNode.html#aa4760135d373af488a08aaeba7114c48',1,'tvm::tir::ScheduleNode']]],
['setspan',['SetSpan',['../classtvm_1_1TypeReporterNode.html#ade00cc26624883a064e9ed2097133cea',1,'tvm::TypeReporterNode']]],
['setstream',['SetStream',['../classtvm_1_1runtime_1_1DeviceAPI.html#adeff47304ec4145d12e0dd20004c7a3d',1,'tvm::runtime::DeviceAPI']]],
@@ -222,7 +225,7 @@ var searchData=
['singleton',['Singleton',['../classtvm_1_1te_1_1Singleton.html',1,'tvm::te::Singleton'],['../classtvm_1_1te_1_1Singleton.html#a94450b853dcd5e9865546d8c8fe351a1',1,'tvm::te::Singleton::Singleton()']]],
['singletonnode',['SingletonNode',['../classtvm_1_1te_1_1SingletonNode.html',1,'tvm::te']]],
['sinh',['sinh',['../namespacetvm.html#ad828bc801c73df761c58d9f8877d52ee',1,'tvm::sinh()'],['../namespacetvm_1_1topi.html#af9694f5470ba2cabc19866be3b00fe8d',1,'tvm::topi::sinh()']]],
- ['size',['Size',['../classtvm_1_1TensorTypeNode.html#a1f08dac86ae8aea81d058ef64cfd38b4',1,'tvm::TensorTypeNode::Size()'],['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#aae5b9ab9f7e497654b90c23a2159a5cc',1,'tvm::meta_schedule::DatabaseNode::Size()'],['../classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a36817d04978253571fef7d01427ce9c0',1,'tvm::meta_schedule::PyDatabaseNode::Size()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1FrameBuffer.html#ae395a0f1c6e79e825aa7a244c74a5d7b',1,' [...]
+ ['size',['size',['../structtvm_1_1relay_1_1Resize1DAttrs.html#afb1175c0ff019e485ed65d98305b5f62',1,'tvm::relay::Resize1DAttrs::size()'],['../structtvm_1_1relay_1_1Resize2DAttrs.html#ab3e26dbbc2dc1da40764832a99459c30',1,'tvm::relay::Resize2DAttrs::size()'],['../structtvm_1_1relay_1_1Resize3DAttrs.html#aab61649fe8417a8a7fbc849090bac083',1,'tvm::relay::Resize3DAttrs::size()'],['../structtvm_1_1relay_1_1LRNAttrs.html#a3758ed1f8a8bcf73008ae1dd2bfa148e',1,'tvm::relay::LRNAttrs::size()'],['.. [...]
['size_5f',['size_',['../classtvm_1_1runtime_1_1MapNode.html#a2285f106f6afa29f512a7818ad59e9e5',1,'tvm::runtime::MapNode']]],
['size_5fbytes',['size_bytes',['../structtvm_1_1tir_1_1usmp_1_1BufferInfoNode.html#a0a5d4bd6072c268df05b90d267b4c0a0',1,'tvm::tir::usmp::BufferInfoNode']]],
['size_5fhint_5fbytes',['size_hint_bytes',['../structtvm_1_1PoolInfoNode.html#ac073aeb75bf031ff8687e132bc112f92',1,'tvm::PoolInfoNode::size_hint_bytes()'],['../structtvm_1_1PoolInfoPropertiesNode.html#aed7c5573ffc8db9424e77e3a85cad120',1,'tvm::PoolInfoPropertiesNode::size_hint_bytes()']]],
@@ -251,7 +254,7 @@ var searchData=
['solvelinearequations',['SolveLinearEquations',['../namespacetvm_1_1arith.html#ae0290f04432523ab8e5f76edde80071a',1,'tvm::arith']]],
['solvelinearinequalities',['SolveLinearInequalities',['../namespacetvm_1_1arith.html#ac59d63560e04431f108e81457b212fdc',1,'tvm::arith']]],
['sorted',['sorted',['../structtvm_1_1relay_1_1UniqueAttrs.html#aef434799646533ec9d796393ba01db44',1,'tvm::relay::UniqueAttrs']]],
- ['source',['Source',['../classtvm_1_1parser_1_1Source.html',1,'tvm::parser::Source'],['../classtvm_1_1arith_1_1IterMarkNode.html#a8b885a675c88e5a5d142fa68bcba048a',1,'tvm::arith::IterMarkNode::source()'],['../classtvm_1_1arith_1_1IterSplitExprNode.html#a7a129dc9b432359a07c1a1e286c3c66f',1,'tvm::arith::IterSplitExprNode::source()'],['../classtvm_1_1parser_1_1SourceNode.html#a51cc3c98e4cdacf0ffdc643c848e09af',1,'tvm::parser::SourceNode::source()'],['../classtvm_1_1tir_1_1ReduceNode.html# [...]
+ ['source',['Source',['../classtvm_1_1parser_1_1Source.html',1,'tvm::parser::Source'],['../classtvm_1_1parser_1_1Source.html#a0ef9f726abcc6c4c9e81b3a257055df8',1,'tvm::parser::Source::Source()'],['../classtvm_1_1arith_1_1IterMarkNode.html#a8b885a675c88e5a5d142fa68bcba048a',1,'tvm::arith::IterMarkNode::source()'],['../classtvm_1_1arith_1_1IterSplitExprNode.html#a7a129dc9b432359a07c1a1e286c3c66f',1,'tvm::arith::IterSplitExprNode::source()'],['../classtvm_1_1parser_1_1SourceNode.html#a51cc [...]
['source_5fmap',['source_map',['../classtvm_1_1IRModuleNode.html#a49470c0bfb4b85d9eda7576a837b7031',1,'tvm::IRModuleNode::source_map()'],['../classtvm_1_1parser_1_1SourceMapNode.html#ae22bc1181b066f17f8938868ef22610a',1,'tvm::parser::SourceMapNode::source_map()']]],
['source_5fmap_2eh',['source_map.h',['../source__map_8h.html',1,'']]],
['source_5fname',['source_name',['../classtvm_1_1DiagnosticBuilder.html#a92d320e1ede24fe5ff47862365002691',1,'tvm::DiagnosticBuilder::source_name()'],['../classtvm_1_1SpanNode.html#ad573167f93facbfbee19983b08bbba3d',1,'tvm::SpanNode::source_name()'],['../classtvm_1_1parser_1_1SourceNode.html#a8d4c50a18eb3e99b14d73d7db2a52af3',1,'tvm::parser::SourceNode::source_name()']]],
@@ -325,7 +328,7 @@ var searchData=
['stagenode',['StageNode',['../classtvm_1_1auto__scheduler_1_1StageNode.html',1,'tvm::auto_scheduler::StageNode'],['../classtvm_1_1te_1_1StageNode.html',1,'tvm::te::StageNode']]],
['stages',['stages',['../classtvm_1_1auto__scheduler_1_1StateNode.html#a881e14990bf228ee3fddb3721c451b9e',1,'tvm::auto_scheduler::StateNode::stages()'],['../classtvm_1_1te_1_1ScheduleNode.html#ab5649969db603d6b7b4d155c0d09cdd5',1,'tvm::te::ScheduleNode::stages()']]],
['stagetoaxesmap',['StageToAxesMap',['../namespacetvm_1_1auto__scheduler.html#a8f12e558fc4b8fbb990e7e204c06beeb',1,'tvm::auto_scheduler']]],
- ['start',['Start',['../classtvm_1_1runtime_1_1TimerNode.html#aa11fc338c39ee2137448e54a10efe0ae',1,'tvm::runtime::TimerNode::Start()'],['../classtvm_1_1runtime_1_1Timer.html#a89bcaa433499bc68902cb473d5eba6ca',1,'tvm::runtime::Timer::Start()'],['../classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#a44fadfb7b0f961a7fb2275e3b5dbcd88',1,'tvm::runtime::profiling::MetricCollectorNode::Start()'],['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#aee5452075c8e022b8aaa6fb365f68e14 [...]
+ ['start',['start',['../structtvm_1_1relay_1_1ArangeAttrs.html#ae8ae5bc1551b406a4f52395af343c2ce',1,'tvm::relay::ArangeAttrs::start()'],['../classtvm_1_1script_1_1printer_1_1SliceDocNode.html#a16de0189a979a6cf9d8f14b39cb5fb54',1,'tvm::script::printer::SliceDocNode::start()'],['../classtvm_1_1runtime_1_1TimerNode.html#aa11fc338c39ee2137448e54a10efe0ae',1,'tvm::runtime::TimerNode::Start()'],['../classtvm_1_1runtime_1_1Timer.html#a89bcaa433499bc68902cb473d5eba6ca',1,'tvm::runtime::Timer::S [...]
['start_5findex',['start_index',['../namespacetvm_1_1topi_1_1nn.html#a752c4130dac73fd2de0390c5f6b24b15',1,'tvm::topi::nn']]],
['startcall',['StartCall',['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#a1fe322f7ba92be44d7e7c8cb184f3833',1,'tvm::runtime::profiling::Profiler']]],
['startmessage',['StartMessage',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#acd512b977c6dd888f90c4fd6d2b9500f',1,'tvm::runtime::micro_rpc::Session']]],
@@ -367,9 +370,9 @@ var searchData=
['stmtsref',['StmtSRef',['../classtvm_1_1tir_1_1StmtSRef.html',1,'tvm::tir::StmtSRef'],['../classtvm_1_1tir_1_1StmtSRef.html#a31687ace5dc4fe487ffb87d658d86412',1,'tvm::tir::StmtSRef::StmtSRef()']]],
['stmtsrefnode',['StmtSRefNode',['../classtvm_1_1tir_1_1StmtSRefNode.html',1,'tvm::tir']]],
['stmtvisitor',['StmtVisitor',['../classtvm_1_1tir_1_1StmtVisitor.html',1,'tvm::tir']]],
- ['stop',['Stop',['../classtvm_1_1runtime_1_1TimerNode.html#a67eb764f2c9e3fb7c2708f01c0c35683',1,'tvm::runtime::TimerNode::Stop()'],['../classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#aca9679dd49dfbc886b9dc99539cbf0e6',1,'tvm::runtime::profiling::MetricCollectorNode::Stop()'],['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#aa2000d8cd1970b5d29139ab1831394f0',1,'tvm::runtime::profiling::Profiler::Stop()'],['../structtvm_1_1relay_1_1ArangeAttrs.html#a1eadf1f3964ca83dad [...]
+ ['stop',['stop',['../structtvm_1_1relay_1_1ArangeAttrs.html#a1eadf1f3964ca83dade8edeae7d6d7cf',1,'tvm::relay::ArangeAttrs::stop()'],['../classtvm_1_1script_1_1printer_1_1SliceDocNode.html#aaeb98937e7617cb76fb9662616b89e81',1,'tvm::script::printer::SliceDocNode::stop()'],['../classtvm_1_1runtime_1_1TimerNode.html#a67eb764f2c9e3fb7c2708f01c0c35683',1,'tvm::runtime::TimerNode::Stop()'],['../classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#aca9679dd49dfbc886b9dc99539cbf0e6',1,' [...]
['stopcall',['StopCall',['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#ad5e6a8e8c9d915c80f494138eedfec3f',1,'tvm::runtime::profiling::Profiler']]],
- ['storage',['Storage',['../classtvm_1_1runtime_1_1vm_1_1Storage.html',1,'tvm::runtime::vm::Storage'],['../classtvm_1_1runtime_1_1vm_1_1Storage.html#aff0c1264864e6205cfa468f069f62f55',1,'tvm::runtime::vm::Storage::Storage()'],['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a3412cabd3b4f42f106f56fc22257f6ca',1,'tvm::runtime::vm::Instruction::storage()']]],
+ ['storage',['Storage',['../classtvm_1_1runtime_1_1vm_1_1Storage.html',1,'tvm::runtime::vm::Storage'],['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a3412cabd3b4f42f106f56fc22257f6ca',1,'tvm::runtime::vm::Instruction::storage()'],['../classtvm_1_1runtime_1_1vm_1_1Storage.html#aff0c1264864e6205cfa468f069f62f55',1,'tvm::runtime::vm::Storage::Storage()']]],
['storage_5falign',['storage_align',['../classtvm_1_1auto__scheduler_1_1State.html#ab006690418e43cc9b7ad021c02657ed6',1,'tvm::auto_scheduler::State::storage_align()'],['../classtvm_1_1te_1_1Stage.html#aa73e3a269d84c3b4f0a1994371d67bab',1,'tvm::te::Stage::storage_align()']]],
['storage_5falignment',['storage_alignment',['../namespacetvm_1_1tir_1_1attr.html#af27d464f2065dc5f77408df7b94d4bb6',1,'tvm::tir::attr']]],
['storage_5fid',['storage_id',['../structTVMGraphExecutorGraphAttr.html#a8a0d6d05adcffbf499aafb6a6700c400',1,'TVMGraphExecutorGraphAttr']]],
@@ -386,7 +389,7 @@ 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(const String &v)'],['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a3511ed66e343f6db16cbd72feda03d5c',1,'tvm::script::printer::LiteralDoc::Str(const TracedObject< String > &v)']]],
+ ['str',['Str',['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a789d7d73bd4d94612fa2a84c16b26b89',1,'tvm::script::printer::LiteralDoc::Str(const String &v)'],['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a3511ed66e343f6db16cbd72feda03d5c',1,'tvm::script::printer::LiteralDoc::Str(const TracedObject< String > &v)'],['../classtvm_1_1TargetNode.html#a30cd67db46a9c4b098a8ba38fff22e26',1,'tvm::TargetNode::str()']]],
['stream',['stream',['../classtvm_1_1ReprPrinter.html#a036409dcdcf6f0ac5c6d7d27ec60ed94',1,'tvm::ReprPrinter']]],
['streamsync',['StreamSync',['../classtvm_1_1runtime_1_1DeviceAPI.html#ac29b9295c432a87658392872c644864f',1,'tvm::runtime::DeviceAPI']]],
['stride',['stride',['../structtvm_1_1relay_1_1YoloReorgAttrs.html#a720c79759a2f2b603b006b0bfcab5fe0',1,'tvm::relay::YoloReorgAttrs::stride()'],['../classtvm_1_1tir_1_1RampNode.html#a618c78e39d18f999dbdd3fe01436f447',1,'tvm::tir::RampNode::stride()']]],
diff --git a/docs/reference/api/doxygen/search/all_15.js b/docs/reference/api/doxygen/search/all_15.js
index aea95601aa..6c4f66ade6 100644
--- a/docs/reference/api/doxygen/search/all_15.js
+++ b/docs/reference/api/doxygen/search/all_15.js
@@ -40,7 +40,7 @@ var searchData=
['takeattrs',['TakeAttrs',['../structtvm_1_1relay_1_1TakeAttrs.html',1,'tvm::relay']]],
['tan',['tan',['../namespacetvm.html#af99838098788d40c80b402f29b3c2e8c',1,'tvm::tan()'],['../namespacetvm_1_1topi.html#a13b757fe52775f43a58d91c0a1330f97',1,'tvm::topi::tan()']]],
['tanh',['tanh',['../namespacetvm.html#a12c5457301d8a2c03a2ba1163edd7cee',1,'tvm::tanh()'],['../namespacetvm_1_1topi.html#aec153e599d33c78a7592007cde1c02cb',1,'tvm::topi::tanh()']]],
- ['target',['Target',['../classtvm_1_1Target.html',1,'tvm::Target'],['../classtvm_1_1auto__scheduler_1_1SearchTaskNode.html#acf4407e0c8dced81b05b34ec0426c933',1,'tvm::auto_scheduler::SearchTaskNode::target()'],['../classtvm_1_1meta__schedule_1_1BuilderInputNode.html#afc001f3e427cfc8c05236b615cfd2868',1,'tvm::meta_schedule::BuilderInputNode::target()'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a45a380cfa2edfd63056fb1a00f9aac35',1,'tvm::meta_schedule::TuningRecordNode::targ [...]
+ ['target',['Target',['../classtvm_1_1Target.html',1,'tvm::Target'],['../classtvm_1_1Target.html#a58a5a1e042e265fe5a6973045226fe1a',1,'tvm::Target::Target(std::nullptr_t)'],['../classtvm_1_1Target.html#a77f3d7cc97d8cfd7172af58b4e784d89',1,'tvm::Target::Target(const String &tag_or_config_or_target_str)'],['../classtvm_1_1Target.html#ab825b350cf478bf948d807b6fdf636a0',1,'tvm::Target::Target(const Map< String, ObjectRef > &config)'],['../classtvm_1_1Target.html#a1abb29217d8e3 [...]
['target_2eh',['target.h',['../target_8h.html',1,'']]],
['target_5fburst_5fbytes',['target_burst_bytes',['../structtvm_1_1PoolInfoNode.html#a747c03e3eafc83b053637b735244c6d7',1,'tvm::PoolInfoNode::target_burst_bytes()'],['../structtvm_1_1PoolInfoPropertiesNode.html#aa1efe29e920f5b003894a2ae3304da17',1,'tvm::PoolInfoPropertiesNode::target_burst_bytes()']]],
['target_5fhost',['target_host',['../classtvm_1_1auto__scheduler_1_1SearchTaskNode.html#afe27bf8cb82dc8a1b6fffb9e5a3e6c20',1,'tvm::auto_scheduler::SearchTaskNode']]],
@@ -74,7 +74,7 @@ var searchData=
['te',['te',['../namespacetvm_1_1te.html',1,'tvm']]],
['tempexpr',['TempExpr',['../classtvm_1_1relay_1_1TempExpr.html',1,'tvm::relay']]],
['tempexprnode',['TempExprNode',['../classtvm_1_1relay_1_1TempExprNode.html',1,'tvm::relay']]],
- ['tensor',['Tensor',['../classtvm_1_1te_1_1Tensor.html',1,'tvm::te::Tensor'],['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a22de469ea5521ba12e14f1e8181bae56',1,'tvm::runtime::vm::Instruction::tensor()'],['../classtvm_1_1te_1_1Tensor.html#afc8d8e74d1c840359661b39514d6fecf',1,'tvm::te::Tensor::Tensor()']]],
+ ['tensor',['Tensor',['../classtvm_1_1te_1_1Tensor.html',1,'tvm::te::Tensor'],['../classtvm_1_1te_1_1Tensor.html#afc8d8e74d1c840359661b39514d6fecf',1,'tvm::te::Tensor::Tensor()'],['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a22de469ea5521ba12e14f1e8181bae56',1,'tvm::runtime::vm::Instruction::tensor()']]],
['tensor_2eh',['tensor.h',['../tensor_8h.html',1,'']]],
['tensor_5fintrin',['tensor_intrin',['../classtvm_1_1te_1_1IterVarAttrNode.html#a6a0d96bbebfd716f851b2ad01738cb3f',1,'tvm::te::IterVarAttrNode']]],
['tensor_5fintrin_2eh',['tensor_intrin.h',['../tensor__intrin_8h.html',1,'']]],
@@ -93,7 +93,7 @@ var searchData=
['tensorintrincall',['TensorIntrinCall',['../classtvm_1_1te_1_1TensorIntrinCall.html',1,'tvm::te::TensorIntrinCall'],['../classtvm_1_1te_1_1TensorIntrinCall.html#a91c10074ce6babeba78fe72a0aab4b52',1,'tvm::te::TensorIntrinCall::TensorIntrinCall()']]],
['tensorintrincallnode',['TensorIntrinCallNode',['../classtvm_1_1te_1_1TensorIntrinCallNode.html',1,'tvm::te']]],
['tensorintrinnode',['TensorIntrinNode',['../classtvm_1_1te_1_1TensorIntrinNode.html',1,'tvm::te::TensorIntrinNode'],['../classtvm_1_1tir_1_1TensorIntrinNode.html',1,'tvm::tir::TensorIntrinNode'],['../classtvm_1_1te_1_1TensorIntrinNode.html#ad59e7f2b881fc798a8c64fd3959f929c',1,'tvm::te::TensorIntrinNode::TensorIntrinNode()']]],
- ['tensorize',['tensorize',['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ae3794a03b566e5b1721b44c564992975',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &loop_rv, const String &intrin)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#aaca1621ab9c3db0ddd04ac57de79d37f',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &block_rv, const String &intrin)=0']]],
+ ['tensorize',['Tensorize',['../classtvm_1_1tir_1_1ScheduleNode.html#ae3794a03b566e5b1721b44c564992975',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &loop_rv, const String &intrin)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#aaca1621ab9c3db0ddd04ac57de79d37f',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &block_rv, const String &intrin)=0'],['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()']]],
['tensornode',['TensorNode',['../classtvm_1_1te_1_1TensorNode.html',1,'tvm::te::TensorNode'],['../classtvm_1_1te_1_1TensorNode.html#a153569448cb1bf9d2924d35639c3b8b8',1,'tvm::te::TensorNode::TensorNode()']]],
['tensors',['tensors',['../classtvm_1_1auto__scheduler_1_1ComputeDAGNode.html#afc71b9ecc0d6b82a5c2ab3250f01514b',1,'tvm::auto_scheduler::ComputeDAGNode::tensors()'],['../classtvm_1_1te_1_1TensorIntrinCallNode.html#a92b543750ea55b9cfd6852139e2ddbd6',1,'tvm::te::TensorIntrinCallNode::tensors()']]],
['tensortype',['TensorType',['../classtvm_1_1TensorType.html',1,'tvm::TensorType'],['../classtvm_1_1TensorType.html#ade4460e9b02b42757a83808dec478b87',1,'tvm::TensorType::TensorType()'],['../namespacetvm_1_1relay.html#a52c13723bba53f4953dfd10c34d480f8',1,'tvm::relay::TensorType()']]],
@@ -225,7 +225,7 @@ var searchData=
['tuningoptionsnode',['TuningOptionsNode',['../classtvm_1_1auto__scheduler_1_1TuningOptionsNode.html',1,'tvm::auto_scheduler']]],
['tuningrecord',['TuningRecord',['../classtvm_1_1meta__schedule_1_1TuningRecord.html',1,'tvm::meta_schedule::TuningRecord'],['../classtvm_1_1meta__schedule_1_1TuningRecord.html#aa4699af50f91bda306e6c199766c4757',1,'tvm::meta_schedule::TuningRecord::TuningRecord()']]],
['tuningrecordnode',['TuningRecordNode',['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html',1,'tvm::meta_schedule']]],
- ['tuple',['Tuple',['../classtvm_1_1relay_1_1Tuple.html',1,'tvm::relay::Tuple'],['../classtvm_1_1relay_1_1Tuple.html#a284e236318986fd385a02aa68bd3e938',1,'tvm::relay::Tuple::Tuple()'],['../classtvm_1_1runtime_1_1ADT.html#a871e902541f0a7e550e74ae0c621994c',1,'tvm::runtime::ADT::Tuple()'],['../classtvm_1_1relay_1_1TupleGetItemPatternNode.html#a1fdd79b2fbbf3d7a14cea7e7efc38574',1,'tvm::relay::TupleGetItemPatternNode::tuple()'],['../classtvm_1_1relay_1_1TupleGetItemNode.html#aade4882f84d828 [...]
+ ['tuple',['Tuple',['../classtvm_1_1relay_1_1Tuple.html',1,'tvm::relay::Tuple'],['../classtvm_1_1relay_1_1TupleGetItemPatternNode.html#a1fdd79b2fbbf3d7a14cea7e7efc38574',1,'tvm::relay::TupleGetItemPatternNode::tuple()'],['../classtvm_1_1relay_1_1TupleGetItemNode.html#aade4882f84d828975c689b5c6b1b68e6',1,'tvm::relay::TupleGetItemNode::tuple()'],['../classtvm_1_1relay_1_1Tuple.html#a284e236318986fd385a02aa68bd3e938',1,'tvm::relay::Tuple::Tuple()'],['../classtvm_1_1runtime_1_1ADT.html#a871 [...]
['tupleaffinetype',['TupleAffineType',['../classtvm_1_1TupleAffineType.html',1,'tvm::TupleAffineType'],['../classtvm_1_1TupleAffineType.html#afced247570984fed7386c147d02efb79',1,'tvm::TupleAffineType::TupleAffineType()']]],
['tupleaffinetypenode',['TupleAffineTypeNode',['../classtvm_1_1TupleAffineTypeNode.html',1,'tvm']]],
['tupledoc',['TupleDoc',['../classtvm_1_1script_1_1printer_1_1TupleDoc.html',1,'tvm::script::printer::TupleDoc'],['../classtvm_1_1script_1_1printer_1_1TupleDoc.html#ac3ec09b672b619376fa70cead671de78',1,'tvm::script::printer::TupleDoc::TupleDoc()'],['../classtvm_1_1script_1_1printer_1_1TupleDoc.html#a78ef6fe46a358a34df8cf8c797ce3d6e',1,'tvm::script::printer::TupleDoc::TupleDoc(Array< ExprDoc > elements)']]],
@@ -483,7 +483,7 @@ var searchData=
['tvmsystemlibentrypoint',['TVMSystemLibEntryPoint',['../runtime_2crt_2module_8h.html#a32fdb5a1df93075a184a36d2549833fa',1,'module.h']]],
['tvmtensorinfo',['TVMTensorInfo',['../structTVMTensorInfo.html',1,'']]],
['tvmvalue',['TVMValue',['../unionTVMValue.html',1,'']]],
- ['type',['Type',['../classtvm_1_1Type.html',1,'tvm::Type'],['../structtvm_1_1detail_1_1is__specialized.html#a3ea7783c457d7ddc82100674292724f4',1,'tvm::detail::is_specialized::type()'],['../structtvm_1_1detail_1_1is__specialized_3_01Container_3_01Args_8_8_8_01_4_00_01Container_01_4.html#a8dee3a1604498d6bc64948f1c0d19dc2',1,'tvm::detail::is_specialized< Container< Args... >, Container >::type()'],['../classtvm_1_1relay_1_1TypePatternNode.html#aab5faa2a58862707b8dc18b59cccac19 [...]
+ ['type',['Type',['../classtvm_1_1Type.html',1,'tvm::Type'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01false_01_4.html#a7925a0702296963f81287ccbb5cfc64f',1,'tvm::detail::TracedObjectWrapperSelector< T, false >::Type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01true_01_4.html#ab1da2c0d7b63a70812c5f27f60aeb695',1,'tvm::detail::TracedObjectWrapperSelector< T, true >::Type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelect [...]
['type_2eh',['type.h',['../ir_2type_8h.html',1,'(Global Namespace)'],['../relay_2type_8h.html',1,'(Global Namespace)']]],
['type_5fannotation',['type_annotation',['../classtvm_1_1relay_1_1VarNode.html#a79a56885eaf2a9326ff490164a5c1f0e',1,'tvm::relay::VarNode::type_annotation()'],['../classtvm_1_1tir_1_1VarNode.html#a7a84c6d137a79e9a5b9c4b6183f18353',1,'tvm::tir::VarNode::type_annotation()']]],
['type_5fargs',['type_args',['../classtvm_1_1relay_1_1CallNode.html#ad23d97a6ae1cc1bea903d4c714f811d6',1,'tvm::relay::CallNode']]],
diff --git a/docs/reference/api/doxygen/search/all_16.js b/docs/reference/api/doxygen/search/all_16.js
index d0cc5f1bbf..2dfa3b02d4 100644
--- a/docs/reference/api/doxygen/search/all_16.js
+++ b/docs/reference/api/doxygen/search/all_16.js
@@ -29,7 +29,7 @@ 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()'],['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#acd41556b0c4088d0f309ef5495aaebe3',1,'tvm::script::ir_builder::tir::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()'],['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#acd41556b0c4088d0f309ef5495aaebe3',1,'tvm::script::ir_builder::tir::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 [...]
['update_5ffunc',['update_func',['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#ade9364c152a36501d4f24fa4f0111519',1,'tvm::auto_scheduler::PythonBasedModelNode']]],
diff --git a/docs/reference/api/doxygen/search/all_17.js b/docs/reference/api/doxygen/search/all_17.js
index 9da3d852e6..4ae1c71445 100644
--- a/docs/reference/api/doxygen/search/all_17.js
+++ b/docs/reference/api/doxygen/search/all_17.js
@@ -18,7 +18,7 @@ var searchData=
['values',['values',['../structTVMArgs.html#ab2d2a8c794bc11fdb56b294e711ff63c',1,'TVMArgs::values()'],['../classtvm_1_1runtime_1_1TVMArgs.html#a3b99059e2f1ad08c99b42b5bee82752f',1,'tvm::runtime::TVMArgs::values()'],['../classtvm_1_1script_1_1printer_1_1DictDocNode.html#a08d71431d889cd4588d57c06c12140c4',1,'tvm::script::printer::DictDocNode::values()']]],
['values_5fcount',['values_count',['../structTVMArgs.html#afa042427dc87d770d0def130f497f3f5',1,'TVMArgs']]],
['valuetypeinfomaker',['ValueTypeInfoMaker',['../structtvm_1_1detail_1_1ValueTypeInfoMaker.html',1,'tvm::detail']]],
- ['var',['Var',['../classtvm_1_1relay_1_1Var.html',1,'tvm::relay::Var'],['../classtvm_1_1tir_1_1Var.html',1,'tvm::tir::Var'],['../classtvm_1_1relay_1_1Var.html#a06ef8ae1d07a5b8a3c25ca7775d17762',1,'tvm::relay::Var::Var(String name_hint, Type type_annotation, Span span=Span())'],['../classtvm_1_1relay_1_1Var.html#a45372a62057ee9332a391e29845505ff',1,'tvm::relay::Var::Var(Id vid, Type type_annotation, Span span=Span())'],['../classtvm_1_1tir_1_1Var.html#a21ba7568a83bfc2a5896f9e0ff181129', [...]
+ ['var',['Var',['../classtvm_1_1relay_1_1Var.html',1,'tvm::relay::Var'],['../classtvm_1_1tir_1_1Var.html',1,'tvm::tir::Var'],['../classtvm_1_1relay_1_1PatternVarNode.html#acfa1269806fbf19e7badd424c19c64bf',1,'tvm::relay::PatternVarNode::var()'],['../classtvm_1_1relay_1_1LetPatternNode.html#aff0c6dec182a3173fe0cb601a5b74ed1',1,'tvm::relay::LetPatternNode::var()'],['../classtvm_1_1relay_1_1LetNode.html#a3a841faeeb71a7e59f99feffb182a7c1',1,'tvm::relay::LetNode::var()'],['../classtvm_1_1scr [...]
['var_2eh',['var.h',['../var_8h.html',1,'']]],
['var_5ftable_2eh',['var_table.h',['../var__table_8h.html',1,'']]],
['vardefframe',['VarDefFrame',['../classtvm_1_1script_1_1printer_1_1VarDefFrame.html',1,'tvm::script::printer::VarDefFrame'],['../classtvm_1_1script_1_1printer_1_1VarDefFrame.html#a8094608662f9111d64ca3eca3b11673a',1,'tvm::script::printer::VarDefFrame::VarDefFrame()']]],
@@ -36,7 +36,7 @@ var searchData=
['vector_5funit_5fbytes',['vector_unit_bytes',['../classtvm_1_1auto__scheduler_1_1HardwareParamsNode.html#a6f2dd9161fdb3233417a9912c8854434',1,'tvm::auto_scheduler::HardwareParamsNode']]],
['vectorcombine',['vectorcombine',['../namespacetvm_1_1tir_1_1builtin.html#a30dff65bc2c142b57fae7f60e378ff43',1,'tvm::tir::builtin']]],
['vectorhigh',['vectorhigh',['../namespacetvm_1_1tir_1_1builtin.html#a45bf65ca7ca01d2016e0b609117d7e25',1,'tvm::tir::builtin']]],
- ['vectorize',['Vectorize',['../classtvm_1_1tir_1_1ScheduleNode.html#ab4a8cd91959ceab22855ec338978bcee',1,'tvm::tir::ScheduleNode::Vectorize()'],['../classtvm_1_1auto__scheduler_1_1State.html#a97b8a21210d63bea241dbab085d89b53',1,'tvm::auto_scheduler::State::vectorize()'],['../classtvm_1_1te_1_1Stage.html#a44d33e3920106e75dc7c68272f880812',1,'tvm::te::Stage::vectorize()']]],
+ ['vectorize',['vectorize',['../classtvm_1_1auto__scheduler_1_1State.html#a97b8a21210d63bea241dbab085d89b53',1,'tvm::auto_scheduler::State::vectorize()'],['../classtvm_1_1te_1_1Stage.html#a44d33e3920106e75dc7c68272f880812',1,'tvm::te::Stage::vectorize()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ab4a8cd91959ceab22855ec338978bcee',1,'tvm::tir::ScheduleNode::Vectorize()']]],
['vectorized',['Vectorized',['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#a2b3df6013772bdd23dfa872b81555272',1,'tvm::script::ir_builder::tir']]],
['vectorizeloop',['VectorizeLoop',['../namespacetvm_1_1tir_1_1transform.html#af3cecb50a8b8fc8021f6a87bc27587da',1,'tvm::tir::transform']]],
['vectorizer',['Vectorizer',['../classtvm_1_1tir_1_1BufferLoadNode.html#a842a72b9d02a9f8541b512478932fece',1,'tvm::tir::BufferLoadNode']]],
diff --git a/docs/reference/api/doxygen/search/all_18.js b/docs/reference/api/doxygen/search/all_18.js
index 783ee22565..f65dce6fc7 100644
--- a/docs/reference/api/doxygen/search/all_18.js
+++ b/docs/reference/api/doxygen/search/all_18.js
@@ -35,7 +35,7 @@ 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_a.js b/docs/reference/api/doxygen/search/all_a.js
index 27a6ae8864..ff187b9b36 100644
--- a/docs/reference/api/doxygen/search/all_a.js
+++ b/docs/reference/api/doxygen/search/all_a.js
@@ -155,7 +155,7 @@ var searchData=
['inverse_5findex_5fmap',['inverse_index_map',['../classtvm_1_1tir_1_1IndexMapNode.html#a5cef05e7862cde95e178fcc5a756b07d',1,'tvm::tir::IndexMapNode']]],
['inverse_5ftransformation',['inverse_transformation',['../classtvm_1_1te_1_1TransformNode.html#a53a5dc162fe1e4a3a51be454ce03bba2',1,'tvm::te::TransformNode']]],
['inverseaffineitermap',['InverseAffineIterMap',['../namespacetvm_1_1arith.html#ae8e8be2bde49ccbe7025f4d7a730e694',1,'tvm::arith']]],
- ['invoke',['Invoke',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#acb19406a24fa95bf39a29d15ad6be256',1,'tvm::runtime::vm::Instruction::Invoke()'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa5f4724e2e702ef9d5c34e85dec53b02',1,'tvm::runtime::vm::VirtualMachine::Invoke(const VMFunction &func, const std::vector< ObjectRef > &args)'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a1094291352e07e4c827a88b1167b89ad',1,'tvm::runtime::vm::VirtualMachine::I [...]
+ ['invoke',['Invoke',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#acb19406a24fa95bf39a29d15ad6be256',1,'tvm::runtime::vm::Instruction::Invoke()'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa5f4724e2e702ef9d5c34e85dec53b02',1,'tvm::runtime::vm::VirtualMachine::Invoke(const VMFunction &func, const std::vector< ObjectRef > &args)'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a1094291352e07e4c827a88b1167b89ad',1,'tvm::runtime::vm::VirtualMachine::I [...]
['invoke_5fargs_5fregisters',['invoke_args_registers',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a6fc678bca0e215303087981a79f23b7f',1,'tvm::runtime::vm::Instruction']]],
['invokeclosure',['InvokeClosure',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#aff2701f8ac1a6232115e73fbb3fe522a',1,'tvm::runtime::vm::Instruction::InvokeClosure()'],['../namespacetvm_1_1runtime_1_1vm.html#a8d8d95ce8d629c7213f2f595917870eca46990b57941483ce17bb07e3af6da59c',1,'tvm::runtime::vm::InvokeClosure()']]],
['invokeglobal',['InvokeGlobal',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a33df7df2ae3019ae1d6bd11427acb747',1,'tvm::runtime::vm::VirtualMachine']]],
diff --git a/docs/reference/api/doxygen/search/all_c.js b/docs/reference/api/doxygen/search/all_c.js
index a906c2c973..2db73b53a4 100644
--- a/docs/reference/api/doxygen/search/all_c.js
+++ b/docs/reference/api/doxygen/search/all_c.js
@@ -113,7 +113,7 @@ var searchData=
['khelp',['kHelp',['../namespacetvm.html#a908c332516a33fdc106cd9ee2ebc2b9ea244ce4b6c7f56eaa446d64fc2d068bbb',1,'tvm']]],
['kifthenelse',['kIfThenElse',['../classtvm_1_1script_1_1printer_1_1OperationDocNode.html#ab096bbea749ee994d75230cd8136afc2aa543c0b05baacb26eb09a6539da0215e',1,'tvm::script::printer::OperationDocNode']]],
['killregister',['KillRegister',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a8a0d04f104703b4b7932acba981401a9',1,'tvm::runtime::vm::Instruction::KillRegister()'],['../namespacetvm_1_1runtime_1_1vm.html#a8d8d95ce8d629c7213f2f595917870eca4dbbdb7762429945fba6aa5906b473ed',1,'tvm::runtime::vm::KillRegister()']]],
- ['kind',['Kind',['../classtvm_1_1script_1_1printer_1_1OperationDocNode.html#ab096bbea749ee994d75230cd8136afc2',1,'tvm::script::printer::OperationDocNode::Kind()'],['../classtvm_1_1TypeVarNode.html#afc08e151afef3c4644ba8d2cd796106a',1,'tvm::TypeVarNode::kind()'],['../classtvm_1_1GlobalTypeVarNode.html#a335e232894a68cc1e0ecb766bf4053c7',1,'tvm::GlobalTypeVarNode::kind()'],['../classtvm_1_1IncompleteTypeNode.html#ab5f37175c1fd0dbbbedc2edaa23d33dc',1,'tvm::IncompleteTypeNode::kind()'],['.. [...]
+ ['kind',['kind',['../classtvm_1_1TypeVarNode.html#afc08e151afef3c4644ba8d2cd796106a',1,'tvm::TypeVarNode::kind()'],['../classtvm_1_1GlobalTypeVarNode.html#a335e232894a68cc1e0ecb766bf4053c7',1,'tvm::GlobalTypeVarNode::kind()'],['../classtvm_1_1IncompleteTypeNode.html#ab5f37175c1fd0dbbbedc2edaa23d33dc',1,'tvm::IncompleteTypeNode::kind()'],['../classtvm_1_1runtime_1_1metadata_1_1MetadataArrayNode.html#a695a21a69be1e72b330abe32c685552e',1,'tvm::runtime::metadata::MetadataArrayNode::kind()' [...]
['kindcheck',['KindCheck',['../namespacetvm_1_1relay.html#a9c09d2d83aa356218069b1def8046ee7',1,'tvm::relay']]],
['kinjective',['kInjective',['../namespacetvm_1_1relay.html#ab5f4d382bf1bee69c3e484ea6c837578a7f703d1ae163ba4e6bef88357a232e00',1,'tvm::relay::kInjective()'],['../namespacetvm_1_1topi.html#a29e22aa45900dad3b6f9f705bb1dc688',1,'tvm::topi::kInjective()']]],
['kinline',['kInline',['../namespacetvm_1_1relay_1_1attr.html#ad294262b6b1ca1b7bf3924a139f17562',1,'tvm::relay::attr::kInline()'],['../namespacetvm_1_1te.html#a7693a274748dadfa2eaa35f5ce9008a5a6472eda35fc70bd00e3ce3b3ce3047fc',1,'tvm::te::kInline()']]],
diff --git a/docs/reference/api/doxygen/search/all_e.js b/docs/reference/api/doxygen/search/all_e.js
index 8ce0e9bbc1..f6547a252d 100644
--- a/docs/reference/api/doxygen/search/all_e.js
+++ b/docs/reference/api/doxygen/search/all_e.js
@@ -73,7 +73,7 @@ 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']]],
diff --git a/docs/reference/api/doxygen/search/functions_10.js b/docs/reference/api/doxygen/search/functions_10.js
index 4db2451470..2005a38839 100644
--- a/docs/reference/api/doxygen/search/functions_10.js
+++ b/docs/reference/api/doxygen/search/functions_10.js
@@ -10,7 +10,7 @@ var searchData=
['pad',['pad',['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi']]],
['padeinsum',['PadEinsum',['../classtvm_1_1tir_1_1ScheduleNode.html#a1ac39c82aee1f8de30d5871d5923fc24',1,'tvm::tir::ScheduleNode']]],
['pagememorymanagercreate',['PageMemoryManagerCreate',['../page__allocator_8h.html#a720dbc7474ac13b93fafb974cfc20bc7',1,'page_allocator.h']]],
- ['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()'],['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#af443e6c0816e4e4ff97881df7a11a6db',1,'tvm::script::ir_builder::tir: [...]
+ ['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()'],['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#af443e6c0816e4e4ff97881df7a11a6db',1,'tvm::script::ir_builder::tir: [...]
['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']]],
@@ -85,6 +85,7 @@ var searchData=
['printdag',['PrintDAG',['../classtvm_1_1auto__scheduler_1_1ComputeDAG.html#a1de07263c59963e3f5a96f275b176471',1,'tvm::auto_scheduler::ComputeDAG']]],
['printdocstring',['PrintDocString',['../classtvm_1_1BaseAttrsNode.html#a80929190102473038bce5b4f6c42dff6',1,'tvm::BaseAttrsNode']]],
['printindent',['PrintIndent',['../classtvm_1_1ReprPrinter.html#a9c5941e7c4e24c9880dbd340cc226bf4',1,'tvm::ReprPrinter']]],
+ ['printinfoandsetinputargs',['PrintInfoAndSetInputArgs',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ac2ca0dc6162002d400e56ccc4c41fb9c',1,'tvm::runtime::vm::VirtualMachine']]],
['printir',['PrintIR',['../namespacetvm_1_1transform.html#a8cca5b98fb5d34e66444343786d85529',1,'tvm::transform']]],
['printstepsaspython',['PrintStepsAsPython',['../classtvm_1_1auto__scheduler_1_1ComputeDAG.html#ace0f0f385d5d3179dd5dc0a1f35990b4',1,'tvm::auto_scheduler::ComputeDAG']]],
['prod',['prod',['../namespacetvm.html#a32a87ae9eacafb2b5b71b28bcc9ef35e',1,'tvm::prod()'],['../namespacetvm_1_1topi.html#a4bc269a40cbdbac3b8b764950820dc8c',1,'tvm::topi::prod()']]],
diff --git a/docs/reference/api/doxygen/search/functions_12.js b/docs/reference/api/doxygen/search/functions_12.js
index 879167f234..73daabc016 100644
--- a/docs/reference/api/doxygen/search/functions_12.js
+++ b/docs/reference/api/doxygen/search/functions_12.js
@@ -59,7 +59,7 @@ var searchData=
['rendererrors',['RenderErrors',['../classtvm_1_1ErrorReporter.html#a54699ec5f538bd207b5aa4e3f55181c6',1,'tvm::ErrorReporter']]],
['renewdefs',['RenewDefs',['../namespacetvm_1_1tir.html#a2e639c81d1c6875ead7764ab8a7cd553',1,'tvm::tir']]],
['renormalizesplitpattern',['RenormalizeSplitPattern',['../namespacetvm_1_1tir_1_1transform.html#a5c670c9efcd740f2f168b62e624c8c57',1,'tvm::tir::transform']]],
- ['reorder',['reorder',['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()']]],
+ ['reorder',['Reorder',['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()'],['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()']]],
['reorderstep',['ReorderStep',['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a83b9dab5f38d5a4d42c6424ba437bc10',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(int stage_id, const Array< Integer > &after_ids)'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a9586534afef3e0f57ab31e8374e70792',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(dmlc::JSONReader *reader)']]],
['reorg',['reorg',['../namespacetvm_1_1topi_1_1vision.html#a1014df582489005202c4218e51792314',1,'tvm::topi::vision']]],
['repeat',['repeat',['../namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687',1,'tvm::topi']]],
@@ -99,7 +99,7 @@ var searchData=
['rewritetensorize',['RewriteTensorize',['../classtvm_1_1meta__schedule_1_1Postproc.html#a95db036cfced4c2575367a26a41498ff',1,'tvm::meta_schedule::Postproc']]],
['rewriteunboundblock',['RewriteUnboundBlock',['../classtvm_1_1meta__schedule_1_1Postproc.html#a1836b2278bc24fdc227c490896d92980',1,'tvm::meta_schedule::Postproc']]],
['rewriteunsafeselect',['RewriteUnsafeSelect',['../namespacetvm_1_1tir_1_1transform.html#a4fe43327c4454dd05b6e925577443f49',1,'tvm::tir::transform']]],
- ['rfactor',['RFactor',['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()'],['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()']]],
+ ['rfactor',['rfactor',['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()']]],
['rfactorstep',['RfactorStep',['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a26e6f85b55307f18fab4469e3bd4be0c',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(int stage_id, int iter_id, int factor_iter_id)'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a95575c21441177634178245ab562cb4f',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(dmlc::JSONReader *reader)']]],
['right_5fshift',['right_shift',['../namespacetvm.html#ae8ecc0382685a855187bede0c97d93e6',1,'tvm::right_shift(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.html#af49dde9dfdeea62e8ad3a6d8db53de0b',1,'tvm::right_shift(const PrimExpr &a, int b, Span span=Span())'],['../namespacetvm.html#a98ff4361d0a24570f8dc32d03cde972a',1,'tvm::right_shift(int a, const PrimExpr &b, Span span=Span())'],['../namespacetvm_1_1topi.html#a9673b9caffb46404b566c3f04a492dfe',1,'tvm::topi:: [...]
['rocblas_5fbatch_5fmatmul',['rocblas_batch_matmul',['../namespacetvm_1_1topi_1_1contrib.html#abf1113dd429e1285752b48f62fe12848',1,'tvm::topi::contrib']]],
@@ -121,7 +121,7 @@ var searchData=
['runafterpass',['RunAfterPass',['../classtvm_1_1instrument_1_1PassInstrumentNode.html#a49332b9ab696afefa427b676dbaba1b0',1,'tvm::instrument::PassInstrumentNode']]],
['runbeforepass',['RunBeforePass',['../classtvm_1_1instrument_1_1PassInstrumentNode.html#a4c5781489ab0113fbfcb9a61e6348b43',1,'tvm::instrument::PassInstrumentNode']]],
['runcallbacks',['RunCallbacks',['../classtvm_1_1auto__scheduler_1_1SearchPolicyNode.html#a4bf8f2f816014b03ebea564d50afeba9',1,'tvm::auto_scheduler::SearchPolicyNode']]],
- ['runloop',['RunLoop',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ad83dfc94ba5e62875df9e780c750487b',1,'tvm::runtime::vm::VirtualMachine']]],
+ ['runloop',['RunLoop',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a08164ef76393a4efb002c1ea6b8ae447',1,'tvm::runtime::vm::VirtualMachine']]],
['runnerfuture',['RunnerFuture',['../classtvm_1_1meta__schedule_1_1RunnerFuture.html#a88baeedd7be0b5cc46083f75a318317f',1,'tvm::meta_schedule::RunnerFuture']]],
['runnerinput',['RunnerInput',['../classtvm_1_1meta__schedule_1_1RunnerInput.html#a46dcc62de7cbe021e381b8c0a5e6776f',1,'tvm::meta_schedule::RunnerInput']]],
['runnerresult',['RunnerResult',['../classtvm_1_1meta__schedule_1_1RunnerResult.html#ad15dac65a62952e661aa5dc639d6a958',1,'tvm::meta_schedule::RunnerResult']]],
diff --git a/docs/reference/api/doxygen/search/functions_13.js b/docs/reference/api/doxygen/search/functions_13.js
index 2e2c1b1569..e9da775751 100644
--- a/docs/reference/api/doxygen/search/functions_13.js
+++ b/docs/reference/api/doxygen/search/functions_13.js
@@ -94,6 +94,8 @@ var searchData=
['setmaxconcurrency',['SetMaxConcurrency',['../namespacetvm_1_1runtime_1_1threading.html#ad66f7fc304b915bebdcfc5c7004016c7',1,'tvm::runtime::threading']]],
['setobject',['SetObject',['../classtvm_1_1runtime_1_1TVMArgsSetter.html#adfc052b0786ef1296d29e0b87f71a03e',1,'tvm::runtime::TVMArgsSetter']]],
['setoneinput',['SetOneInput',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#ab66c1484cfb630914dd41da36ab91db1',1,'tvm::runtime::vm::VirtualMachine']]],
+ ['setoutputs',['SetOutputs',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a2ee3a67f145ed44cabfb4d456c048445',1,'tvm::runtime::vm::VirtualMachine']]],
+ ['setoutputtensorstoregister',['SetOutputTensorsToRegister',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a95a0552177a93f4839ab431756efeaf3',1,'tvm::runtime::vm::VirtualMachine']]],
['setscope',['SetScope',['../classtvm_1_1tir_1_1ScheduleNode.html#aa4760135d373af488a08aaeba7114c48',1,'tvm::tir::ScheduleNode']]],
['setspan',['SetSpan',['../classtvm_1_1TypeReporterNode.html#ade00cc26624883a064e9ed2097133cea',1,'tvm::TypeReporterNode']]],
['setstream',['SetStream',['../classtvm_1_1runtime_1_1DeviceAPI.html#adeff47304ec4145d12e0dd20004c7a3d',1,'tvm::runtime::DeviceAPI']]],
@@ -134,7 +136,7 @@ var searchData=
['singlepoint',['SinglePoint',['../classtvm_1_1arith_1_1IntSet.html#a58aeb0d34656b1b43ac2532e4dfa12ed',1,'tvm::arith::IntSet']]],
['singleton',['Singleton',['../classtvm_1_1te_1_1Singleton.html#a94450b853dcd5e9865546d8c8fe351a1',1,'tvm::te::Singleton']]],
['sinh',['sinh',['../namespacetvm.html#ad828bc801c73df761c58d9f8877d52ee',1,'tvm::sinh()'],['../namespacetvm_1_1topi.html#af9694f5470ba2cabc19866be3b00fe8d',1,'tvm::topi::sinh()']]],
- ['size',['Size',['../classtvm_1_1TensorTypeNode.html#a1f08dac86ae8aea81d058ef64cfd38b4',1,'tvm::TensorTypeNode::Size()'],['../classtvm_1_1meta__schedule_1_1DatabaseNode.html#aae5b9ab9f7e497654b90c23a2159a5cc',1,'tvm::meta_schedule::DatabaseNode::Size()'],['../classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a36817d04978253571fef7d01427ce9c0',1,'tvm::meta_schedule::PyDatabaseNode::Size()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1FrameBuffer.html#ae395a0f1c6e79e825aa7a244c74a5d7b',1,' [...]
+ ['size',['size',['../classtvm_1_1runtime_1_1ADT.html#af51613add20f67643684b1c7fdd5569a',1,'tvm::runtime::ADT::size()'],['../classtvm_1_1runtime_1_1ArrayNode.html#a3e88cee6eb31d0e495f7debd94b7573d',1,'tvm::runtime::ArrayNode::size()'],['../classtvm_1_1runtime_1_1Array.html#aed6387e67d18b9d5ad18f510fd600a25',1,'tvm::runtime::Array::size()'],['../classtvm_1_1runtime_1_1MapNode.html#a5c0c770f7667f911aa8bec879e3ac214',1,'tvm::runtime::MapNode::size()'],['../classtvm_1_1runtime_1_1Map.html#a [...]
['sizevar',['SizeVar',['../classtvm_1_1tir_1_1SizeVar.html#ac470249315d9e395ad581d35dd5dcb05',1,'tvm::tir::SizeVar::SizeVar(ObjectPtr< Object > n)'],['../classtvm_1_1tir_1_1SizeVar.html#a0f8cb8a92feb96343939d223db90f7cd',1,'tvm::tir::SizeVar::SizeVar(String name_hint="s", DataType t=DataType::Int(32), Span span=Span())']]],
['skipassert',['SkipAssert',['../namespacetvm_1_1tir_1_1transform.html#a6fdd5910b00af823071dcdddd21cd2d3',1,'tvm::tir::transform']]],
['slice',['Slice',['../classtvm_1_1te_1_1Tensor_1_1Slice.html#ab314819e8bcca6421e9a4f33e48578c3',1,'tvm::te::Tensor::Slice']]],
@@ -197,7 +199,7 @@ 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(const String &v)'],['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a3511ed66e343f6db16cbd72feda03d5c',1,'tvm::script::printer::LiteralDoc::Str(const TracedObject< String > &v)']]],
+ ['str',['Str',['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a789d7d73bd4d94612fa2a84c16b26b89',1,'tvm::script::printer::LiteralDoc::Str(const String &v)'],['../classtvm_1_1script_1_1printer_1_1LiteralDoc.html#a3511ed66e343f6db16cbd72feda03d5c',1,'tvm::script::printer::LiteralDoc::Str(const TracedObject< String > &v)'],['../classtvm_1_1TargetNode.html#a30cd67db46a9c4b098a8ba38fff22e26',1,'tvm::TargetNode::str()']]],
['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']]],
['strided_5fslice_5fwith_5faxes',['strided_slice_with_axes',['../namespacetvm_1_1topi.html#acd9415b24624edac4edec4802d275062',1,'tvm::topi']]],
diff --git a/docs/reference/api/doxygen/search/functions_14.js b/docs/reference/api/doxygen/search/functions_14.js
index 4b6a21e84e..3c3bbbe90a 100644
--- a/docs/reference/api/doxygen/search/functions_14.js
+++ b/docs/reference/api/doxygen/search/functions_14.js
@@ -20,7 +20,7 @@ var searchData=
['tensorintrin',['TensorIntrin',['../classtvm_1_1te_1_1TensorIntrin.html#a4ff4237911227bf80b3076906dc3b7ea',1,'tvm::te::TensorIntrin::TensorIntrin()'],['../classtvm_1_1tir_1_1TensorIntrin.html#af5a94c7b098b56056e02eaf187e6871c',1,'tvm::tir::TensorIntrin::TensorIntrin()']]],
['tensorintrincall',['TensorIntrinCall',['../classtvm_1_1te_1_1TensorIntrinCall.html#a91c10074ce6babeba78fe72a0aab4b52',1,'tvm::te::TensorIntrinCall']]],
['tensorintrinnode',['TensorIntrinNode',['../classtvm_1_1te_1_1TensorIntrinNode.html#ad59e7f2b881fc798a8c64fd3959f929c',1,'tvm::te::TensorIntrinNode']]],
- ['tensorize',['tensorize',['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ae3794a03b566e5b1721b44c564992975',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &loop_rv, const String &intrin)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#aaca1621ab9c3db0ddd04ac57de79d37f',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &block_rv, const String &intrin)=0']]],
+ ['tensorize',['Tensorize',['../classtvm_1_1tir_1_1ScheduleNode.html#ae3794a03b566e5b1721b44c564992975',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &loop_rv, const String &intrin)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#aaca1621ab9c3db0ddd04ac57de79d37f',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &block_rv, const String &intrin)=0'],['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()']]],
['tensornode',['TensorNode',['../classtvm_1_1te_1_1TensorNode.html#a153569448cb1bf9d2924d35639c3b8b8',1,'tvm::te::TensorNode']]],
['tensortype',['TensorType',['../classtvm_1_1TensorType.html#ade4460e9b02b42757a83808dec478b87',1,'tvm::TensorType']]],
['terminalrenderer',['TerminalRenderer',['../namespacetvm.html#a69a0e3f559d3a3b98d42701117d93ed0',1,'tvm']]],
diff --git a/docs/reference/api/doxygen/search/functions_15.js b/docs/reference/api/doxygen/search/functions_15.js
index 249d84d88a..ee28582590 100644
--- a/docs/reference/api/doxygen/search/functions_15.js
+++ b/docs/reference/api/doxygen/search/functions_15.js
@@ -22,7 +22,7 @@ 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()'],['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#acd41556b0c4088d0f309ef5495aaebe3',1,'tvm::script::ir_builder::tir::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()'],['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#acd41556b0c4088d0f309ef5495aaebe3',1,'tvm::script::ir_builder::tir::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_16.js b/docs/reference/api/doxygen/search/functions_16.js
index 445caa1454..c545b38266 100644
--- a/docs/reference/api/doxygen/search/functions_16.js
+++ b/docs/reference/api/doxygen/search/functions_16.js
@@ -10,7 +10,7 @@ var searchData=
['vector',['Vector',['../classtvm_1_1arith_1_1IntSet.html#a29b6f1e60f4b328fcfabc514e0c10f17',1,'tvm::arith::IntSet']]],
['vectorcombine',['vectorcombine',['../namespacetvm_1_1tir_1_1builtin.html#a30dff65bc2c142b57fae7f60e378ff43',1,'tvm::tir::builtin']]],
['vectorhigh',['vectorhigh',['../namespacetvm_1_1tir_1_1builtin.html#a45bf65ca7ca01d2016e0b609117d7e25',1,'tvm::tir::builtin']]],
- ['vectorize',['Vectorize',['../classtvm_1_1tir_1_1ScheduleNode.html#ab4a8cd91959ceab22855ec338978bcee',1,'tvm::tir::ScheduleNode::Vectorize()'],['../classtvm_1_1auto__scheduler_1_1State.html#a97b8a21210d63bea241dbab085d89b53',1,'tvm::auto_scheduler::State::vectorize()'],['../classtvm_1_1te_1_1Stage.html#a44d33e3920106e75dc7c68272f880812',1,'tvm::te::Stage::vectorize()']]],
+ ['vectorize',['vectorize',['../classtvm_1_1auto__scheduler_1_1State.html#a97b8a21210d63bea241dbab085d89b53',1,'tvm::auto_scheduler::State::vectorize()'],['../classtvm_1_1te_1_1Stage.html#a44d33e3920106e75dc7c68272f880812',1,'tvm::te::Stage::vectorize()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ab4a8cd91959ceab22855ec338978bcee',1,'tvm::tir::ScheduleNode::Vectorize()']]],
['vectorized',['Vectorized',['../namespacetvm_1_1script_1_1ir__builder_1_1tir.html#a2b3df6013772bdd23dfa872b81555272',1,'tvm::script::ir_builder::tir']]],
['vectorizeloop',['VectorizeLoop',['../namespacetvm_1_1tir_1_1transform.html#af3cecb50a8b8fc8021f6a87bc27587da',1,'tvm::tir::transform']]],
['vectorjacobianproduct',['VectorJacobianProduct',['../namespacetvm_1_1te.html#a547183f5a311af53ab598faba423fd64',1,'tvm::te']]],
diff --git a/docs/reference/api/doxygen/search/functions_9.js b/docs/reference/api/doxygen/search/functions_9.js
index b41e52c0c4..a1643964fb 100644
--- a/docs/reference/api/doxygen/search/functions_9.js
+++ b/docs/reference/api/doxygen/search/functions_9.js
@@ -74,7 +74,7 @@ var searchData=
['invalidatecache',['InvalidateCache',['../classtvm_1_1te_1_1ScheduleNode.html#a2b6a92ec4b1c295604b55ff8e8c365e7',1,'tvm::te::ScheduleNode']]],
['inverse',['Inverse',['../classtvm_1_1tir_1_1IndexMap.html#a5363f3897623b7854aed24b2fd657f5a',1,'tvm::tir::IndexMap']]],
['inverseaffineitermap',['InverseAffineIterMap',['../namespacetvm_1_1arith.html#ae8e8be2bde49ccbe7025f4d7a730e694',1,'tvm::arith']]],
- ['invoke',['Invoke',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#acb19406a24fa95bf39a29d15ad6be256',1,'tvm::runtime::vm::Instruction::Invoke()'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa5f4724e2e702ef9d5c34e85dec53b02',1,'tvm::runtime::vm::VirtualMachine::Invoke(const VMFunction &func, const std::vector< ObjectRef > &args)'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a1094291352e07e4c827a88b1167b89ad',1,'tvm::runtime::vm::VirtualMachine::I [...]
+ ['invoke',['Invoke',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#acb19406a24fa95bf39a29d15ad6be256',1,'tvm::runtime::vm::Instruction::Invoke()'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa5f4724e2e702ef9d5c34e85dec53b02',1,'tvm::runtime::vm::VirtualMachine::Invoke(const VMFunction &func, const std::vector< ObjectRef > &args)'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a1094291352e07e4c827a88b1167b89ad',1,'tvm::runtime::vm::VirtualMachine::I [...]
['invokeclosure',['InvokeClosure',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#aff2701f8ac1a6232115e73fbb3fe522a',1,'tvm::runtime::vm::Instruction']]],
['invokeglobal',['InvokeGlobal',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a33df7df2ae3019ae1d6bd11427acb747',1,'tvm::runtime::vm::VirtualMachine']]],
['invokepacked',['InvokePacked',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a83bcfbc103e576eac9a225ab1912c1e4',1,'tvm::runtime::vm::Instruction::InvokePacked()'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a89bc186467de25e51802e0ce739f436b',1,'tvm::runtime::vm::VirtualMachine::InvokePacked()']]],
diff --git a/docs/reference/api/doxygen/search/functions_d.js b/docs/reference/api/doxygen/search/functions_d.js
index c62c0111db..0e4e05ff5a 100644
--- a/docs/reference/api/doxygen/search/functions_d.js
+++ b/docs/reference/api/doxygen/search/functions_d.js
@@ -37,7 +37,7 @@ 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/doxygen/search/typedefs_f.js b/docs/reference/api/doxygen/search/typedefs_f.js
index d02f81c990..1fc2ccb057 100644
--- a/docs/reference/api/doxygen/search/typedefs_f.js
+++ b/docs/reference/api/doxygen/search/typedefs_f.js
@@ -42,7 +42,7 @@ var searchData=
['tvmretvalue',['TVMRetValue',['../classtvm_1_1BaseAttrsNode.html#a1f56f080d0c1fab79d9469029aef8ebb',1,'tvm::BaseAttrsNode']]],
['tvmretvaluehandle',['TVMRetValueHandle',['../c__runtime__api_8h.html#a6cd1076476117e74454f67931c2da1d4',1,'c_runtime_api.h']]],
['tvmstreamhandle',['TVMStreamHandle',['../c__runtime__api_8h.html#ab1d5f6b7945e1410602a8a057fda5757',1,'c_runtime_api.h']]],
- ['type',['type',['../structtvm_1_1detail_1_1is__specialized.html#a3ea7783c457d7ddc82100674292724f4',1,'tvm::detail::is_specialized::type()'],['../structtvm_1_1detail_1_1is__specialized_3_01Container_3_01Args_8_8_8_01_4_00_01Container_01_4.html#a8dee3a1604498d6bc64948f1c0d19dc2',1,'tvm::detail::is_specialized< Container< Args... >, Container >::type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01false_01_4.html#a7925a0702296963f81287ccbb5cfc64f',1,'tv [...]
+ ['type',['Type',['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01false_01_4.html#a7925a0702296963f81287ccbb5cfc64f',1,'tvm::detail::TracedObjectWrapperSelector< T, false >::Type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01T_00_01true_01_4.html#ab1da2c0d7b63a70812c5f27f60aeb695',1,'tvm::detail::TracedObjectWrapperSelector< T, true >::Type()'],['../structtvm_1_1detail_1_1TracedObjectWrapperSelector_3_01Map_3_01K_00_01V_01_4_00_01true_01_4 [...]
['typecall',['TypeCall',['../namespacetvm_1_1relay.html#ab406a37acee11226e3e2e119beee439e',1,'tvm::relay']]],
['typecallnode',['TypeCallNode',['../namespacetvm_1_1relay.html#af4dccabc877b8fd7db47cb73fb93883e',1,'tvm::relay']]],
['typeconstraint',['TypeConstraint',['../namespacetvm_1_1relay.html#a64e2e93fe04716efd8334ab4e39c92ce',1,'tvm::relay']]],
diff --git a/docs/reference/api/doxygen/search/variables_11.js b/docs/reference/api/doxygen/search/variables_11.js
index 75971a813c..515909aa17 100644
--- a/docs/reference/api/doxygen/search/variables_11.js
+++ b/docs/reference/api/doxygen/search/variables_11.js
@@ -29,6 +29,7 @@ var searchData=
['seq_5findex',['seq_index',['../classtvm_1_1tir_1_1StmtSRefNode.html#a1ce9920064b0c2ed42be0e9412fd3939',1,'tvm::tir::StmtSRefNode']]],
['sequalreduce',['SEqualReduce',['../structtvm_1_1detail_1_1ImplSEqualReduce.html#a2069b17f164be27516b0ca7b53b74d49',1,'tvm::detail::ImplSEqualReduce::SEqualReduce()'],['../structtvm_1_1detail_1_1SelectSEqualReduce.html#a6de180df5c5b0cec0e62f75e576259cb',1,'tvm::detail::SelectSEqualReduce::SEqualReduce()']]],
['session_5fid',['session_id',['../structtvm_1_1runtime_1_1micro__rpc_1_1SessionHeader.html#ae3a24ea6c4a1569d540f1d5330bf73d5',1,'tvm::runtime::micro_rpc::SessionHeader']]],
+ ['set_5foutputs_5fenabled_5f',['set_outputs_enabled_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a6a3eb3eb9362ee6567e9ee6a6bc7ccf9',1,'tvm::runtime::vm::VirtualMachine']]],
['setargs',['SetArgs',['../structTVMPackedFunc.html#a455396ff85d8e8cff95e39ae15ad5cc6',1,'TVMPackedFunc']]],
['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']]],
diff --git a/docs/reference/api/doxygen/search/variables_e.js b/docs/reference/api/doxygen/search/variables_e.js
index 2693489ea0..958bbd561f 100644
--- a/docs/reference/api/doxygen/search/variables_e.js
+++ b/docs/reference/api/doxygen/search/variables_e.js
@@ -27,5 +27,7 @@ var searchData=
['output_5fplaceholders',['output_placeholders',['../classtvm_1_1te_1_1ExternOpNode.html#a004d2ec4a439339a2067e4fe7b93dac8',1,'tvm::te::ExternOpNode']]],
['output_5fshape',['output_shape',['../structtvm_1_1relay_1_1SparseToDenseAttrs.html#a96725ff7c8a481e81a2fd0ad163b4ecf',1,'tvm::relay::SparseToDenseAttrs']]],
['output_5fsize',['output_size',['../structtvm_1_1relay_1_1AdaptivePool1DAttrs.html#a18b0e1c79c534fec9eabb0656a395c9e',1,'tvm::relay::AdaptivePool1DAttrs::output_size()'],['../structtvm_1_1relay_1_1AdaptivePool2DAttrs.html#a545f40ec0dbdf52f628bebcc23a63950',1,'tvm::relay::AdaptivePool2DAttrs::output_size()'],['../structtvm_1_1relay_1_1AdaptivePool3DAttrs.html#a0c56cb9665840dcc8e949c41d39c710d',1,'tvm::relay::AdaptivePool3DAttrs::output_size()'],['../structtvm_1_1runtime_1_1vm_1_1Instru [...]
- ['outputs',['outputs',['../structTVMMetadata.html#ae98ddb5d3a598ab923d8cadc66d38632',1,'TVMMetadata::outputs()'],['../classtvm_1_1te_1_1HybridOpNode.html#a6ff8e6faa8d01063e32a2c124721df29',1,'tvm::te::HybridOpNode::outputs()'],['../classtvm_1_1te_1_1ScheduleNode.html#a27b0f687f7b20fcc6416a49e041712d8',1,'tvm::te::ScheduleNode::outputs()'],['../classtvm_1_1tir_1_1InstructionNode.html#a745f994b096890961ed67b17f2040bba',1,'tvm::tir::InstructionNode::outputs()']]]
+ ['output_5ftensor_5freg_5findices_5f',['output_tensor_reg_indices_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#aa98e90db9a3ef70c732b5322171023c2',1,'tvm::runtime::vm::VirtualMachine']]],
+ ['outputs',['outputs',['../structTVMMetadata.html#ae98ddb5d3a598ab923d8cadc66d38632',1,'TVMMetadata::outputs()'],['../classtvm_1_1te_1_1HybridOpNode.html#a6ff8e6faa8d01063e32a2c124721df29',1,'tvm::te::HybridOpNode::outputs()'],['../classtvm_1_1te_1_1ScheduleNode.html#a27b0f687f7b20fcc6416a49e041712d8',1,'tvm::te::ScheduleNode::outputs()'],['../classtvm_1_1tir_1_1InstructionNode.html#a745f994b096890961ed67b17f2040bba',1,'tvm::tir::InstructionNode::outputs()']]],
+ ['outputs_5f',['outputs_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a43d9a2e6056305a8c14941eb08f2cf29',1,'tvm::runtime::vm::VirtualMachine']]]
];
diff --git a/docs/reference/api/doxygen/search/variables_f.js b/docs/reference/api/doxygen/search/variables_f.js
index 833cc5525a..26c1c2e366 100644
--- a/docs/reference/api/doxygen/search/variables_f.js
+++ b/docs/reference/api/doxygen/search/variables_f.js
@@ -57,6 +57,7 @@ var searchData=
['prefix_5f',['prefix_',['../classtvm_1_1NameSupplyNode.html#aa14405ac3611e27389632477779fb6ad',1,'tvm::NameSupplyNode']]],
['preflattened_5fbuffer_5fmap',['preflattened_buffer_map',['../classtvm_1_1script_1_1ir__builder_1_1tir_1_1PrimFuncFrameNode.html#afb98c531e14362a920bebf1cb0c1bac1',1,'tvm::script::ir_builder::tir::PrimFuncFrameNode::preflattened_buffer_map()'],['../classtvm_1_1tir_1_1PrimFuncNode.html#abf5f197a2cef15f3f1fecafa09358ffc',1,'tvm::tir::PrimFuncNode::preflattened_buffer_map()']]],
['preprocessor',['preprocessor',['../classtvm_1_1TargetKindNode.html#a47f02c66d0f972befdfb29ec592ecba0',1,'tvm::TargetKindNode']]],
+ ['preresult_5fop_5findex_5f',['preresult_op_index_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a37b4a705186bf76cb9aa5168dcbc3651',1,'tvm::runtime::vm::VirtualMachine']]],
['primitive_5fmap',['primitive_map',['../classtvm_1_1runtime_1_1vm_1_1Executable.html#ab5a31e8670a4f20564abc48610a90e8c',1,'tvm::runtime::vm::Executable']]],
['primitive_5ftargets',['primitive_targets',['../classtvm_1_1CompilationConfigNode.html#aaf237580f1684eaf97e1852c6b69ecbd',1,'tvm::CompilationConfigNode']]],
['priority',['priority',['../classtvm_1_1auto__scheduler_1_1RPCRunnerNode.html#ad5c143b5ce09e135fb8c318d3c0042b9',1,'tvm::auto_scheduler::RPCRunnerNode']]],
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 1f52cbcc27..85a44c2708 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 d332f23a11..8281c55b07 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/9a4514116/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 67738e4951..4a794bc0a4 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/9a4514116/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 b1df098a88..12d74fbb9d 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/9a4514116/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 73b7d94509..59baa0cd82 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/9a4514116/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 bf41786b31..699664a17e 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/9a4514116/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 8eaf5c3b99..cd85a27525 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/9a4514116/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 becb4f432e..921c031e6e 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/9a4514116/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 686a4d9496..4550cb7daf 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/9a4514116/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 f8be7ba3f2..b15032ac4d 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/9a4514116/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 ae3f9759d4..6f3825f851 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/9a4514116/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 a2ca2b262d..d98550956d 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/9a4514116/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 decb2de253..fcae9f1476 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/9a4514116/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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 e17ce2efda..d11f44e444 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/9a4514116/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/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/9a4514116/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3e3d900c6/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
... 1816 lines suppressed ...