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 2023/03/22 11:10:33 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@c7970ddd79a1e6bbf5e07ab2c515ec4991242ef7)
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 b8c39a5cf9 deploying docs (apache/tvm@c7970ddd79a1e6bbf5e07ab2c515ec4991242ef7)
b8c39a5cf9 is described below
commit b8c39a5cf9a2e133a86627875fc8e0b9f2ad3983
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Mar 22 11:10:25 2023 +0000
deploying docs (apache/tvm@c7970ddd79a1e6bbf5e07ab2c515ec4991242ef7)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 339681 -> 333957 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24019 -> 23827 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_model_on_adreno_tvmc.rst.txt | 2 +-
.../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 | 22 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 785 ++++++++++++++++-----
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 76 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 89 ++-
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 14 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../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 | 4 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 59 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/genindex.html | 2 +
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 8 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_adreno_tvmc.html | 37 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 31 +-
docs/how_to/deploy_models/deploy_prequantized.html | 7 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 39 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 785 ++++++++++++++++-----
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 76 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 89 ++-
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 14 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/install/nnpack.html | 12 +-
docs/objects.inv | Bin 24737 -> 24746 bytes
.../classtvm_1_1tir_1_1ScheduleNode-members.html | 9 +-
.../doxygen/classtvm_1_1tir_1_1ScheduleNode.html | 60 +-
...lasstvm_1_1tir_1_1ScheduleNode__coll__graph.svg | 2 +-
...stvm_1_1tir_1_1ScheduleNode__inherit__graph.svg | 2 +-
docs/reference/api/doxygen/database_8h_source.html | 2 +-
docs/reference/api/doxygen/functions_func_u.html | 5 +-
docs/reference/api/doxygen/functions_p.html | 2 +-
docs/reference/api/doxygen/functions_s.html | 4 +-
docs/reference/api/doxygen/functions_t.html | 6 +-
docs/reference/api/doxygen/functions_u.html | 5 +-
docs/reference/api/doxygen/functions_v.html | 10 +-
.../api/doxygen/measure__candidate_8h_source.html | 2 +-
docs/reference/api/doxygen/postproc_8h_source.html | 2 +-
.../api/doxygen/schedule__rule_8h_source.html | 2 +-
docs/reference/api/doxygen/search/all_11.js | 4 +-
docs/reference/api/doxygen/search/all_13.js | 4 +-
docs/reference/api/doxygen/search/all_14.js | 6 +-
docs/reference/api/doxygen/search/all_15.js | 4 +-
docs/reference/api/doxygen/search/all_16.js | 3 +-
docs/reference/api/doxygen/search/all_17.js | 2 +-
docs/reference/api/doxygen/search/all_18.js | 2 +-
docs/reference/api/doxygen/search/all_a.js | 2 +-
docs/reference/api/doxygen/search/all_e.js | 2 +-
docs/reference/api/doxygen/search/functions_12.js | 2 +-
docs/reference/api/doxygen/search/functions_14.js | 2 +-
docs/reference/api/doxygen/search/functions_15.js | 3 +-
docs/reference/api/doxygen/search/functions_d.js | 2 +-
.../doxygen/tir_2schedule_2schedule_8h_source.html | 4 +-
docs/reference/api/doxygen/trace_8h_source.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/tir.html | 96 ++-
.../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 +-
docs/reference/api/typedoc/classes/instance.html | 58 +-
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 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../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 | 124 ++--
.../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 | 4 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 269 ++++---
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 18 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
162 files changed, 2381 insertions(+), 1469 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 3bff224219..b0c19c3436 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 45939926ac..475ea5ff8a 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 1ce8eca8a3..5cdf8746fa 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.041 seconds)
+ **Total running time of the script:** ( 1 minutes 14.499 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index bf8dd56b40..76b1d99a9b 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2bfba95b-33ca-4d8e-a98f-ccfd04165508 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip49313ea3-fb03-47d7-9a25-3b1593e9dd18 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 41f62ec50c..2549167229 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ 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, 63.2MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 60.6MB/s]
65%|######4 | 26.8M/41.5M [00:00<00:00, 80.6MB/s]
85%|########5 | 35.4M/41.5M [00:00<00:00, 84.0MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 82.3MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
38%|###7 | 15.8M/41.5M [00:00<00:00, 165MB/s]
76%|#######5 | 31.5M/41.5M [00:00<00:00, 120MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 92.5MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 8d8f022a6d..0fddeb7258 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
27%|##7 | 12.1M/44.7M [00:00<00:00, 127MB/s]
54%|#####4 | 24.2M/44.7M [00:00<00:00, 108MB/s]
78%|#######7 | 34.7M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
23%|##3 | 10.4M/44.7M [00:00<00:00, 109MB/s]
49%|####8 | 21.7M/44.7M [00:00<00:00, 114MB/s]
73%|#######2 | 32.5M/44.7M [00:00<00:00, 106MB/s]
96%|#########5| 42.7M/44.7M [00:00<00:00, 105MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/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 5806994445..74ab3d4299 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -430,7 +430,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 30.355 seconds)
+ **Total running time of the script:** ( 1 minutes 29.769 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 8d22785208..7a7165e869 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
=================
-**06:43.278** total execution time for **how_to_compile_models** files:
+**06:34.582** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:30.355 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:29.769 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:18.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:14.499 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:55.973 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:54.993 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:37.531 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:37.144 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.077 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:31.072 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.209 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.588 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.507 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.603 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.233 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.270 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.689 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.044 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.663 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.600 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 21495eb428..de25986aee 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -637,7 +637,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2537.5753 2536.9458 2541.9001 2535.6260 1.7455
+ 2633.5339 2632.5954 2636.6337 2631.3362 1.8132
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
index e7c83e9241..38e971960a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
@@ -127,7 +127,7 @@ Make a Keras Resnet50 Model
.. code-block:: none
Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
-
8192/102967424 [..............................] - ETA: 0s
8028160/102967424 [=>............................] - ETA: 0s
13099008/102967424 [==>...........................] - ETA: 0s
16769024/102967424 [===>..........................] - ETA: 0s
25960448/102967424 [======>.......................] - ETA: 0s
27353088/102967424 [======>.......................] - ETA: 0s
36700160/102967424 [=========>....................] - ETA: 0s
41746432/102967424 [===========>..................] - ETA: 0s
46751744/102967424 [============>.................] - ETA: 0s
51724288/102967424 [==============>...............] - ETA: 0s
56696832/102967424 [===============>..............] - ETA: 0s
61841408/102967424 [=================>............] - ETA: 0s
66813952/102967424 [==================>...........] - ETA: 0s
71811072/102967424 [===================>..........] - ETA: 0s
76816384/102967424 [=====================>........] - ETA: 0s
81895424/102967424 [======================>.......] -
ETA: 0s
86900736/102967424 [========================>.....] - ETA: 0s
91996160/102967424 [=========================>....] - ETA: 0s
94461952/102967424 [==========================>...] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
+
8192/102967424 [..............................] - ETA: 0s
8781824/102967424 [=>............................] - ETA: 0s
14123008/102967424 [===>..........................] - ETA: 0s
19128320/102967424 [====>.........................] - ETA: 0s
24190976/102967424 [======>.......................] - ETA: 0s
29106176/102967424 [=======>......................] - ETA: 0s
33546240/102967424 [========>.....................] - ETA: 0s
39165952/102967424 [==========>...................] - ETA: 0s
44228608/102967424 [===========>..................] - ETA: 0s
49201152/102967424 [=============>................] - ETA: 0s
54231040/102967424 [==============>...............] - ETA: 0s
58851328/102967424 [================>.............] - ETA: 0s
64323584/102967424 [=================>............] - ETA: 0s
69328896/102967424 [===================>..........] - ETA: 0s
74326016/102967424 [====================>.........] - ETA: 0s
79405056/102967424 [======================>.......] -
ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
91701248/102967424 [=========================>....] - ETA: 0s
96755712/102967424 [===========================>..] - ETA: 0s
101720064/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
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 91ac8bd8e7..129ec3657e 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
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9343 15.8414 16.5317 15.4561 0.4044
+ 15.7434 15.5668 16.3996 15.4081 0.3556
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 88c1b6b4f2..2833f58936 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
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
9%|9 | 16.0M/170M [00:00<00:01, 124MB/s]
16%|#6 | 27.8M/170M [00:00<00:01, 103MB/s]
24%|##3 | 40.0M/170M [00:00<00:01, 103MB/s]
29%|##9 | 49.8M/170M [00:00<00:01, 96.5MB/s]
35%|###4 | 59.0M/170M [00:00<00:01, 86.2MB/s]
41%|#### | 69.1M/170M [00:00<00:01, 91.9MB/s]
47%|####7 | 80.1M/170M [00:00<00:00, 95.6MB/s]
56%|#####6 | 95.1M/170M [00:00<00:00, 113MB/s]
63%|######2 | 106M/170M [00:01<00:00, 98.3MB/s]
72%|#######2 | 123M/170M [00:01<00:00, 118MB/s]
79%|#######9 | 135M/170M [00:01<00:00, 115MB/s]
86%|########6 | 146M/170M [00:01<00:00, 94.7MB/s]
94%|#########4| 160M/170M [00:01<00:00, 108MB/s]
100%|##########| 170M/170M [00:01<00:00, 101MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|8 | 14.8M/170M [00:00<00:01, 154MB/s]
17%|#7 | 29.5M/170M [00:00<00:01, 117MB/s]
24%|##4 | 41.2M/170M [00:00<00:01, 85.0MB/s]
32%|###2 | 54.7M/170M [00:00<00:01, 101MB/s]
40%|#### | 68.0M/170M [00:00<00:00, 112MB/s]
47%|####6 | 79.6M/170M [00:00<00:00, 108MB/s]
53%|#####3 | 90.5M/170M [00:00<00:00, 102MB/s]
59%|#####9 | 101M/170M [00:01<00:00, 96.6MB/s]
66%|######5 | 112M/170M [00:01<00:00, 102MB/s]
72%|#######2 | 123M/170M [00:01<00:00, 106MB/s]
78%|#######8 | 133M/170M [00:01<00:00, 103MB/s]
84%|########4 | 143M/170M [00:01<00:00, 103MB/s]
90%|######### | 153M/170M [00:01<00:00, 102MB/s]
96%|#########5| 163M/170M [00:01<00:00, 91.7MB/s]
100%|##########| 170M/170M [00:01<00:00, 103MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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:124: 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').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 31.442 seconds)
+ **Total running time of the script:** ( 3 minutes 34.974 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 7a211bd8a7..fd7f16f8fb 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 165MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
97%|#########6| 13.1M/13.6M [00:00<00:00, 137MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 134MB/s]
@@ -409,7 +409,7 @@ 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)
- 90.0796 89.9686 94.8404 89.7732 0.5329
+ 90.7131 90.5405 100.1469 90.0935 1.1737
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.009 seconds)
+ **Total running time of the script:** ( 1 minutes 16.198 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 4fdedd52e6..5d27084881 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
@@ -423,7 +423,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.8698 119.0240 120.6894 117.1571 1.0432
+ 121.0229 121.0042 125.9077 120.1047 0.6011
@@ -460,7 +460,7 @@ 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 36.447 seconds)
+ **Total running time of the script:** ( 2 minutes 38.451 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 a2fc979169..7d99a7eb6d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 27.191 seconds)
+ **Total running time of the script:** ( 1 minutes 22.408 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 acc854f115..951fe4fd08 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
@@ -170,7 +170,7 @@ 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]
1%| | 1290/132723 [00:00<00:10, 12856.33KB/s]
3%|3 | 4431/132723 [00:00<00:05, 23750.83KB/s]
9%|8 | 11598/132723 [00:00<00:02, 45610.37KB/s]
15%|#5 | 19965/132723 [00:00<00:01, 60623.44KB/s]
21%|##1 | 28481/132723 [00:00<00:01, 69464.55KB/s]
28%|##7 | 37009/132723 [00:00<00:01, 74835.88KB/s]
34%|###4 | 45589/132723 [00:00<00:01, 78417.04KB/s]
41%|#### | 54099/132723 [00:00<00:00, 80542.81KB/s]
47%|####7 | 62751/132723 [00:00<00:00, 82407.76KB/s]
54%|#####3 | 71407/132723 [00:01<00:00, 83687.72KB/s]
60%|###### | 79991/132723 [00:01<00:00, 84344.23KB/s]
67%|######6 | 88518/132723 [00:01<00:00, 84624.02KB/s]
73%|#######3 | 97126/132723 [00:01<00:00, 85063.11KB/s]
80%|#######9 | 105750/132723 [00:01<00:00, 85416.07KB/s]
86%|########6 | 114376/132723 [00:01<00:00, 85667.63KB/s]
93%|#########2
| 122986/132723 [00:01<00:00, 85796.13KB/s]
99%|#########9| 131566/132723 [00:01<00:00, 85640.52KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77310.60KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
1%| | 1248/132723 [00:00<00:10, 12478.76KB/s]
3%|2 | 3964/132723 [00:00<00:06, 21113.97KB/s]
7%|7 | 9818/132723 [00:00<00:03, 38201.63KB/s]
13%|#3 | 17794/132723 [00:00<00:02, 54605.70KB/s]
19%|#9 | 25817/132723 [00:00<00:01, 63840.41KB/s]
26%|##5 | 33886/132723 [00:00<00:01, 69567.18KB/s]
32%|###1 | 41937/132723 [00:00<00:01, 73141.67KB/s]
38%|###7 | 49993/132723 [00:00<00:01, 75498.80KB/s]
44%|####3 | 58114/132723 [00:00<00:00, 77283.15KB/s]
50%|####9 | 66281/132723 [00:01<00:00, 78633.05KB/s]
56%|#####6 | 74361/132723 [00:01<00:00, 79285.91KB/s]
62%|######2 | 82488/132723 [00:01<00:00, 79887.63KB/s]
68%|######8 | 90625/132723 [00:01<00:00, 80331.27KB/s]
74%|#######4 | 98785/132723 [00:01<00:00, 80708.59KB/s]
81%|######## | 106923/132723 [00:01<00:00, 80909.46KB/s]
87%|########6 |
115044/132723 [00:01<00:00, 80997.32KB/s]
93%|#########2| 123165/132723 [00:01<00:00, 81059.43KB/s]
99%|#########8| 131316/132723 [00:01<00:00, 81193.32KB/s]
100%|##########| 132723/132723 [00:01<00:00, 72945.48KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 49.127 seconds)
+ **Total running time of the script:** ( 3 minutes 58.651 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 cd166f1bb8..a6133eacdb 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
@@ -5,28 +5,28 @@
Computation times
=================
-**16:05.175** total execution time for **how_to_deploy_models** files:
+**16:16.493** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:49.127 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:58.651 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:31.442 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:34.974 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:36.447 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:38.451 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:27.191 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:22.408 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:16.009 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:16.198 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.568 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.318 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:50.899 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:50.645 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.435 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.791 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.691 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.743 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.360 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.309 | 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 35b102244d..7753085d24 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
@@ -463,7 +463,7 @@ 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.zip6ff600c0-da71-4dbf-bfd3-84804c390e08 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip71c6cead-917c-423a-81ab-efebafaddae3 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 aefce660de..39e0aa64c3 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
=================
-**00:53.519** total execution time for **how_to_extend_tvm** files:
+**00:57.556** 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``) | 00:49.800 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:53.530 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.676 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.889 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.037 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.130 | 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 43f2d59222..293d16c790 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
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 22172us [22172us] (48.81%; 48.81%)
- FoldScaleAxis: 23250us [6us] (51.19%; 51.19%)
- FoldConstant: 23244us [1685us] (51.17%; 99.97%)
- InferType: 21560us [21560us] (47.47%; 92.75%)
+ InferType: 22850us [22850us] (48.68%; 48.68%)
+ FoldScaleAxis: 24087us [9us] (51.32%; 51.32%)
+ FoldConstant: 24078us [1740us] (51.30%; 99.96%)
+ InferType: 22338us [22338us] (47.59%; 92.77%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 21499us [21499us] (48.32%; 48.32%)
- FoldScaleAxis: 22992us [5us] (51.68%; 51.68%)
- FoldConstant: 22987us [1635us] (51.67%; 99.98%)
- InferType: 21352us [21352us] (47.99%; 92.89%)
+ InferType: 22513us [22513us] (48.37%; 48.37%)
+ FoldScaleAxis: 24031us [8us] (51.63%; 51.63%)
+ FoldConstant: 24023us [1768us] (51.61%; 99.97%)
+ InferType: 22255us [22255us] (47.81%; 92.64%)
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 4e54d71b2b..73026e5f4f 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
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 52.217887 ms
+ Convolution: 53.653087 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 78c15eac96..c0774a157c 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
@@ -598,7 +598,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.246758 ms
+ conv2d with tensor core: 12.069520 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 3766026241..ba02b06ab3 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018414
- Baseline: 3.343532
+ Numpy running time: 0.018164
+ Baseline: 3.435242
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.299235
+ Opt1: 0.291741
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.333744
+ Opt2: 0.337721
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.119433
+ Opt3: 0.120061
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110272
+ Opt4: 0.109663
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111860
+ Opt5: 0.111426
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147597
+ Opt6: 0.146630
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 fe04fd745e..e43492e244 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
=================
-**00:35.301** total execution time for **how_to_optimize_operators** files:
+**00:35.377** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.209 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.395 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.912 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.831 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.181 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.151 | 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 9ef3631be9..693eba5e6c 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
=================
-**10:07.542** total execution time for **how_to_tune_with_autoscheduler** files:
+**10:11.975** 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``) | 06:14.710 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:14.017 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:42.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:46.369 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:10.615 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:11.970 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.158 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:13.964 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.069 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.400 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.392 | 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 9882a1b835..e0c7b4c581 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
@@ -243,117 +243,346 @@ cooperative fetching, unrolling and operator fusion.
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- blockIdx_x = T.launch_thread("blockIdx.x", 56)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([84], "float32", "shared")
- kernel_shared = T.allocate([768], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 32)
- conv2d_nchw_1 = T.Buffer((49,), data=conv2d_nchw, scope="local", align=16)
+ blockIdx_x = T.launch_thread("blockIdx.x", 32)
+ conv2d_nchw = T.allocate([16], "float32", "local")
+ pad_temp_shared = T.allocate([1296], "float32", "shared")
+ kernel_shared = T.allocate([2304], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 49)
+ conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[6] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
+ conv2d_nchw_1[14] = T.float32(0)
+ conv2d_nchw_1[1] = T.float32(0)
+ conv2d_nchw_1[3] = T.float32(0)
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(128, 3):
- cse_var_4: T.int32 = rc_outer_outer * 196
- cse_var_3: T.int32 = ry_outer_outer * 7
- cse_var_2: T.int32 = rc_outer_outer * 36
- cse_var_1: T.int32 = ry_outer_outer * 3
+ conv2d_nchw_1[15] = T.float32(0)
+ for rc_outer_outer in range(32):
+ cse_var_2: T.int32 = rc_outer_outer * 784
+ cse_var_1: T.int32 = rc_outer_outer * 144
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((84,), data=pad_temp_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((1296,), data=pad_temp_shared, scope="shared")
data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 32):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 21 // 3 + ry_outer_outer and threadIdx_x_1 % 21 // 3 + ry_outer_outer < 8 and 1 <= blockIdx_x % 7 + threadIdx_x_1 % 3 and blockIdx_x % 7 + threadIdx_x_1 % 3 < 8, data_1[cse_var_4 + threadIdx_x_1 // 3 * 7 + cse_var_3 + blockIdx_x % 7 + threadIdx_x_1 % 3 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 32):
- pad_temp_shared_1[threadIdx_x_1 + 32] = T.if_then_else(1 <= (threadIdx_x_1 + 11) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 + 11) % 21 // 3 + ry_outer_outer < 8 and 1 <= blockIdx_x % 7 + (threadIdx_x_1 + 2) % 3 and blockIdx_x % 7 + (threadIdx_x_1 + 2) % 3 < 8, data_1[cse_var_4 + (threadIdx_x_1 + 32) // 3 * 7 + cse_var_3 + blockIdx_x % 7 + (threadIdx_x_1 + 2) % 3 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 32):
- if T.likely(threadIdx_x_1 < 20):
- pad_temp_shared_1[threadIdx_x_1 + 64] = T.if_then_else(1 <= (threadIdx_x_1 + 1) // 3 + ry_outer_outer and (threadIdx_x_1 + 1) // 3 + ry_outer_outer < 8 and 1 <= blockIdx_x % 7 + (threadIdx_x_1 + 1) % 3 and blockIdx_x % 7 + (threadIdx_x_1 + 1) % 3 < 8, data_1[cse_var_4 + (threadIdx_x_1 + 64) // 3 * 7 + cse_var_3 + blockIdx_x % 7 + (threadIdx_x_1 + 1) % 3 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 49] = T.if_then_else(9 <= (threadIdx_x_1 + 49) % 81 and (threadIdx_x_1 + 49) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 49) // 81 * 49 + (threadIdx_x_1 + 49) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 81 * 49 + (threadIdx_x_1 + 17) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 147] = T.if_then_else(9 <= (threadIdx_x_1 + 66) % 81 and (threadIdx_x_1 + 66) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 147) // 81 * 49 + (threadIdx_x_1 + 66) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(9 <= (threadIdx_x_1 + 34) % 81 and (threadIdx_x_1 + 34) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 81 * 49 + (threadIdx_x_1 + 34) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 245] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 245) // 81 * 49 + (threadIdx_x_1 + 2) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(9 <= (threadIdx_x_1 + 51) % 81 and (threadIdx_x_1 + 51) % 81 < 72 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 81 * 49 + (threadIdx_x_1 + 51) % 81 // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 343] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 343) // 81 * 49 + (threadIdx_x_1 + 19) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(9 <= (threadIdx_x_1 + 68) % 81 and (threadIdx_x_1 + 68) % 81 < 72 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 81 * 49 + (threadIdx_x_1 + 68) % 81 // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 441] = T.if_then_else(1 <= (threadIdx_x_1 // 9 + 4) % 9 and (threadIdx_x_1 + 36) % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 441) // 81 * 49 + (threadIdx_x_1 // 9 + 4) % 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(5 <= threadIdx_x_1 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 81 * 49 + (threadIdx_x_1 + 4) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 539] = T.if_then_else(9 <= (threadIdx_x_1 + 53) % 81 and (threadIdx_x_1 + 53) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 539) // 81 * 49 + (threadIdx_x_1 + 53) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 81 * 49 + (threadIdx_x_1 + 21) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 637] = T.if_then_else(9 <= (threadIdx_x_1 + 70) % 81 and (threadIdx_x_1 + 70) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 637) // 81 * 49 + (threadIdx_x_1 + 70) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(9 <= (threadIdx_x_1 + 38) % 81 and (threadIdx_x_1 + 38) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 81 * 49 + (threadIdx_x_1 + 38) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 735] = T.if_then_else(3 <= threadIdx_x_1 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 735) // 81 * 49 + (threadIdx_x_1 + 6) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(9 <= (threadIdx_x_1 + 55) % 81 and (threadIdx_x_1 + 55) % 81 < 72 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 81 * 49 + (threadIdx_x_1 + 55) % 81 // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 833] = T.if_then_else(1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 833) // 81 * 49 + (threadIdx_x_1 + 23) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(1 <= (threadIdx_x_1 // 9 + 8) % 9 and (threadIdx_x_1 + 72) % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 882) // 81 * 49 + (threadIdx_x_1 // 9 + 8) % 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 931] = T.if_then_else(9 <= (threadIdx_x_1 + 40) % 81 and (threadIdx_x_1 + 40) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 931) // 81 * 49 + (threadIdx_x_1 + 40) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else(1 <= threadIdx_x_1 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 81 * 49 + (threadIdx_x_1 + 8) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1029] = T.if_then_else(9 <= (threadIdx_x_1 + 57) % 81 and (threadIdx_x_1 + 57) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1029) // 81 * 49 + (threadIdx_x_1 + 57) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else(threadIdx_x_1 < 47 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 81 * 49 + (threadIdx_x_1 + 25) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1127] = T.if_then_else(9 <= (threadIdx_x_1 + 74) % 81 and (threadIdx_x_1 + 74) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1127) // 81 * 49 + (threadIdx_x_1 + 74) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else(9 <= (threadIdx_x_1 + 42) % 81 and (threadIdx_x_1 + 42) % 81 < 72 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 81 * 49 + (threadIdx_x_1 + 42) % 81 // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1225] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1225) // 81 * 49 + (threadIdx_x_1 + 10) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ if T.likely(threadIdx_x_1 < 22):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else(threadIdx_x_1 < 13 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 81 * 49 + (threadIdx_x_1 + 59) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((768,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((2304,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 32) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 32) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 64) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 64) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 96] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 36864]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 128) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 128) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 160) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 160) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 192] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 73728]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 224) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 224) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 256) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 256) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 288] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 110592]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 320) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 320) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 352) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 352) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 384] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 147456]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 416) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 416) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 448) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 448) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 480] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 184320]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 512) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 512) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 544) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 544) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 576] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 221184]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 608) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 608) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 640) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 640) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 258048]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 704) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 704) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 736) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 736) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- for rc_outer_inner, yy_outer_inner in T.grid(2, 7):
- cse_var_11: T.int32 = yy_outer_inner + 7
- cse_var_10: T.int32 = rc_outer_inner * 42 + yy_outer_inner * 3
- cse_var_9: T.int32 = cse_var_10 + 23
- cse_var_8: T.int32 = cse_var_10 + 22
- cse_var_7: T.int32 = cse_var_10 + 21
- cse_var_6: T.int32 = cse_var_10 + 2
- cse_var_5: T.int32 = cse_var_10 + 1
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_10] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_10] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 384]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_5] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 1]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_5] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 385]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_6] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 2]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_6] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 386]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_7] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 3]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_7] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 387]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_8] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 4]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_8] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 388]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_9] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 5]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_9] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 389]
- for i2_inner in range(7):
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 49] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2 + 49]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 98) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 147] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 147) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 3]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 52]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 245] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 245) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 101) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 6]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 343] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 343) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 55]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 392] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 104) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 441] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 441) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 9]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 490] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 58]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 539] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 539) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 107) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 588] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 588) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 12]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 637] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 637) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 61]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 686] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 686) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 110) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 735] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 735) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 15]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 784) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 64]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 833] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 833) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 113) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 882] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 882) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 18]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 931] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 931) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 67]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 980] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 980) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 116) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1029] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1029) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 21]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1078] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1078) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 70]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1127] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1127) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 119) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1176] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1176) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 24]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1225] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1225) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 73]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1274] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1274) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 122) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1323] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1323) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 27]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1372] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1372) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 76]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1421] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1421) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 125) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1470] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1470) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 30]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1519] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1519) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 79]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1568) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1617] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1617) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 33]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1666] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1666) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 82]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1715] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1715) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 131) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1764] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1764) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 36]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1813] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1813) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 85]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1862] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1862) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 134) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1911] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1911) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 39]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1960] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1960) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 88]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2009] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2009) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 137) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2058] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2058) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 42]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2107] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2107) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 91]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2156] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2156) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 140) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2205] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2205) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 45]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2254] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2254) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 94]
+ with T.launch_thread(threadIdx_x_2, 49):
+ if T.likely(threadIdx_x_2 < 1):
+ kernel_shared_1[threadIdx_x_2 + 2303] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2303) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 143]
+ for rc_inner in range(16):
+ cse_var_3: T.int32 = rc_inner * 9
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 288]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 576]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 864]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1152]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1440]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1728]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 2016]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 144]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 432]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 720]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1008]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1296]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1584]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1872]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 2160]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 289]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 577]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 865]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1153]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1441]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1729]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 2017]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 145]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 433]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 721]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1009]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1297]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1585]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1873]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 2161]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 290]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 578]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 866]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1154]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1442]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1730]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 2018]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 146]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 434]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 722]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1010]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1298]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1586]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1874]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 2162]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 291]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 579]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 867]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1155]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1443]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1731]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 2019]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 147]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 435]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 723]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1011]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1299]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1587]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1875]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 2163]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 292]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 580]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 868]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1156]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1444]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1732]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 2020]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 148]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 436]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 724]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1012]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1300]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1588]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1876]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 2164]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 293]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 581]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 869]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1157]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1445]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1733]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 2021]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 149]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 437]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 725]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1013]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1301]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1589]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1877]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 2165]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 294]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 582]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 870]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1158]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1446]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1734]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 2022]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 150]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 438]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 726]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1014]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1302]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1590]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1878]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 2166]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 295]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 583]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 871]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1159]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1447]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1735]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 2023]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 151]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 439]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 727]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1015]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1303]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1591]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1879]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 2167]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 296]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 584]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 872]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1160]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1448]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1736]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 2024]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 152]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 440]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 728]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1016]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1304]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1592]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1880]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 2168]
+ for i1_inner in range(2):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x // 7 * 3136 + threadIdx_x * 49 + i2_inner * 7 + blockIdx_x % 7] = T.max(conv2d_nchw_1[i2_inner] + bias_1[blockIdx_x // 7 * 64 + threadIdx_x], T.float32(0))
- compute_1[blockIdx_x // 7 * 3136 + threadIdx_x * 49 + i2_inner * 7 + blockIdx_x % 7 + 1568] = T.max(conv2d_nchw_1[i2_inner + 7] + bias_1[blockIdx_x // 7 * 64 + threadIdx_x + 32], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 98] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 16 + i1_inner + 2], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 196] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 16 + i1_inner + 4], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 294] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_1[blockIdx_x * 16 + i1_inner + 6], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 392] = T.max(conv2d_nchw_1[i1_inner + 8] + bias_1[blockIdx_x * 16 + i1_inner + 8], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 490] = T.max(conv2d_nchw_1[i1_inner + 10] + bias_1[blockIdx_x * 16 + i1_inner + 10], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 588] = T.max(conv2d_nchw_1[i1_inner + 12] + bias_1[blockIdx_x * 16 + i1_inner + 12], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 686] = T.max(conv2d_nchw_1[i1_inner + 14] + bias_1[blockIdx_x * 16 + i1_inner + 14], T.float32(0))
@@ -403,7 +632,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.422 ms
+ Execution time of this operator: 0.273 ms
@@ -451,21 +680,21 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
- 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=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=8)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=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_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
@@ -473,14 +702,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=8)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -500,14 +729,14 @@ 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=32)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 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:
@@ -525,78 +754,264 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[84];
- __shared__ float kernel_shared[768];
+ extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[16];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[2304];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((1 <= ((((((int)threadIdx.x) + 11) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 11) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 32) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) [...]
- if (((int)threadIdx.x) < 20) {
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= (((((int)threadIdx.x) + 1) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) + 1) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 64) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.0000 [...]
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 32) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 32) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 64) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((((((int)threadIdx.x) + 128) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 160) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 160) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((((((int)threadIdx.x) + 224) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 224) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 256) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((((((int)threadIdx.x) + 320) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 352) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 352) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((((((int)threadIdx.x) + 416) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 416) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 448) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((((((int)threadIdx.x) + 512) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 544) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 544) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((((((int)threadIdx.x) + 608) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 608) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 640) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((((((int)threadIdx.x) + 704) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 736) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 736) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((rc_outer_inner * 42) + (yy_outer_inner * 3))] * kernel_shared[((((int)threadIdx.x) * 12) + (rc_outer_inner * 6))]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((rc_outer_inner * 42) + (yy_outer_inner * 3))] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 384)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 1)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 1)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 385)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 2)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 2)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 386)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 21)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 21)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 387)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 22)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 22)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 388)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 23)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 23)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 389)]));
- }
- }
+ conv2d_nchw[15] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = (((((9 <= ((((int)threadIdx.x) + 70) % 81)) && (((((int)threadIdx.x) + 70) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 637) / 81) * 49)) + ((((((int)threadIdx.x) + 70) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 735)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 735) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 833)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 833) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((9 <= ((((int)threadIdx.x) + 40) % 81)) && (((((int)threadIdx.x) + 40) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 931) / 81) * 49)) + ((((((int)threadIdx.x) + 40) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 980) / 81) * 49)) + (((((int)threadIdx.x) + 8) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((9 <= ((((int)threadIdx.x) + 57) % 81)) && (((((int)threadIdx.x) + 57) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1029) / 81) * 49)) + ((((((int)threadIdx.x) + 57) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + (((((int)threadIdx.x) + 25) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1127) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1225) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 22) {
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + (((((int)threadIdx.x) + 59) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 49)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 98) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 147) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 3)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 52)];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 245) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 101) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 343) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 55)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 104) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 441)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 441) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9)];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 58)];
+ kernel_shared[(((int)threadIdx.x) + 539)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 539) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 107) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 637)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 637) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 61)];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 110) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 735)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 735) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 15)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64)];
+ kernel_shared[(((int)threadIdx.x) + 833)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 833) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 113) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 18)];
+ kernel_shared[(((int)threadIdx.x) + 931)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 931) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 67)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 116) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1029) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 21)];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 70)];
+ kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1127) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 119) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1225)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1225) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 73)];
+ kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 122) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1323)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1323) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 27)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 76)];
+ kernel_shared[(((int)threadIdx.x) + 1421)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1421) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 125) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 30)];
+ kernel_shared[(((int)threadIdx.x) + 1519)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1519) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 79)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1617)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1617) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 33)];
+ kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 82)];
+ kernel_shared[(((int)threadIdx.x) + 1715)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1715) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 131) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 1813)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1813) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 85)];
+ kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 134) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1911)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1911) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 39)];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 88)];
+ kernel_shared[(((int)threadIdx.x) + 2009)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2009) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 137) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 42)];
+ kernel_shared[(((int)threadIdx.x) + 2107)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2107) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 91)];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 140) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 2205)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2205) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 45)];
+ kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 94)];
+ if (((int)threadIdx.x) < 1) {
+ kernel_shared[(((int)threadIdx.x) + 2303)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2303) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 143)];
+ }
+ __syncthreads();
+ for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_inner * 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 288)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 576)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 864)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1152)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1440)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1728)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 2016)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 432)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 720)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1008)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1296)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1584)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1872)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 2160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 289)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 577)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 865)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1153)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1441)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1729)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 2017)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 145)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 433)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 721)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1009)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1297)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1585)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1873)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 2161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 290)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 578)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 866)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1154)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1442)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1730)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 2018)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 146)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 434)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 722)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1010)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1298)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1586)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1874)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 2162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 291)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 579)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 867)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1155)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1443)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1731)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 2019)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 147)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 435)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 723)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1011)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1299)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1587)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1875)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 2163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 292)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 580)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 868)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1156)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1444)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1732)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 2020)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 148)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 436)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 724)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1012)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1300)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1588)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1876)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 2164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 293)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 581)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 869)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1157)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1445)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1733)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 2021)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 149)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 437)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 725)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1013)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1301)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1589)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1877)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 2165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 294)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 582)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 870)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1158)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1446)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1734)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 2022)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 150)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 438)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 726)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1014)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1302)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1590)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1878)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 2166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 295)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 583)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 871)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1159)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1447)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1735)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 2023)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 151)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 439)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 727)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1015)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1303)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1591)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1879)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 2167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 296)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 584)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 872)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1160)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1448)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1736)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 2024)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 152)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 440)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 728)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1016)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1304)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1592)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1880)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 2168)]));
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7)) + 1568)] = max((conv2d_nchw[(i2_inner + 7)] + bias[((((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x)) + 32)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 2)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 294)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 6)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 490)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 10)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 12)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 686)] = max((conv2d_nchw[(i1_inner + 14)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 14)]), 0.000000e+00f);
}
}
@@ -656,7 +1071,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 14.710 seconds)
+ **Total running time of the script:** ( 6 minutes 14.017 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 d91fe1f97b..ca7dc54c6f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.0860 8.0890 8.0948 8.0743 0.0086
+ 8.1509 8.1473 8.1641 8.1413 0.0096
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.615 seconds)
+ **Total running time of the script:** ( 1 minutes 11.970 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
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 50e61973c3..d4e062b31c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 759.8484 759.4011 760.9119 759.2323 0.7551
+ 767.9541 766.9722 770.3072 766.5829 1.6715
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 42.353 seconds)
+ **Total running time of the script:** ( 1 minutes 46.369 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 78144fe20a..bf86244a1d 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
@@ -389,74 +389,26 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(128):
- compute_1 = T.allocate([512], "float32", "global")
- compute_2 = T.Buffer((512,), data=compute_1)
+ for i0_outer_i1_outer_fused in T.parallel(64):
+ compute_1 = T.allocate([1024], "float32", "global")
+ compute_2 = T.Buffer((1024,), data=compute_1)
for nb_j_inner in range(2):
- for i_inner_init in range(16):
- cse_var_1: T.int32 = i_inner_init * 32 + nb_j_inner * 16
- compute_2[cse_var_1] = T.float32(0)
- compute_2[cse_var_1 + 1] = T.float32(0)
- compute_2[cse_var_1 + 2] = T.float32(0)
- compute_2[cse_var_1 + 3] = T.float32(0)
- compute_2[cse_var_1 + 4] = T.float32(0)
- compute_2[cse_var_1 + 5] = T.float32(0)
- compute_2[cse_var_1 + 6] = T.float32(0)
- compute_2[cse_var_1 + 7] = T.float32(0)
- compute_2[cse_var_1 + 8] = T.float32(0)
- compute_2[cse_var_1 + 9] = T.float32(0)
- compute_2[cse_var_1 + 10] = T.float32(0)
- compute_2[cse_var_1 + 11] = T.float32(0)
- compute_2[cse_var_1 + 12] = T.float32(0)
- compute_2[cse_var_1 + 13] = T.float32(0)
- compute_2[cse_var_1 + 14] = T.float32(0)
- compute_2[cse_var_1 + 15] = T.float32(0)
- for elem_idx, i_inner in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 16):
- cse_var_2 = T.int32()
+ for i_inner_init, j_init in T.grid(32, 16):
+ compute_2[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 32, 16):
+ cse_var_1 = T.int32()
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_21: T.int32 = elem_idx * 16
- cse_var_20: T.int32 = i_inner * 32 + nb_j_inner * 16
- cse_var_19: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_18: T.int32 = i0_outer_i1_outer_fused // 16 * 4096 + i_inner * 256
- cse_var_17: T.int32 = cse_var_20 + 9
- cse_var_16: T.int32 = cse_var_20 + 8
- cse_var_15: T.int32 = cse_var_20 + 7
- cse_var_14: T.int32 = cse_var_20 + 6
- cse_var_13: T.int32 = cse_var_20 + 5
- cse_var_12: T.int32 = cse_var_20 + 4
- cse_var_11: T.int32 = cse_var_20 + 3
- cse_var_10: T.int32 = cse_var_20 + 2
- cse_var_9: T.int32 = cse_var_20 + 15
- cse_var_8: T.int32 = cse_var_20 + 14
- cse_var_7: T.int32 = cse_var_20 + 13
- cse_var_6: T.int32 = cse_var_20 + 12
- cse_var_5: T.int32 = cse_var_20 + 11
- cse_var_4: T.int32 = cse_var_20 + 10
- cse_var_3: T.int32 = cse_var_20 + 1
+ cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- for i0_inner in range(16):
- cse_var_22: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 8192 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner, i1_inner in T.grid(32, 32):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_22:cse_var_22 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_22:cse_var_22 + 32], T.Broadcast(T.float32(0), 32))
+ compute_3[cse_var_4] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_4], T.float32(0))
@@ -506,7 +458,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.674 ms
+ Execution time of this operator: 1.661 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 d9239020f5..d87b6e20ae 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:31.101** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.709** 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``) | 00:31.066 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:44.671 | 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``) | 00:00.024 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.004 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.004 | 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 b36ab16420..cadcde65f0 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
@@ -390,8 +390,11 @@ 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 875, 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, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9685816
- 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, 1, 8, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1656577
+ No: 2 GFLOPS: 240.37/240.37 result: MeasureResult(costs=(0.000963099981981982,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8540472984313965, timestamp=1679480318.6655898) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4775456
+ No: 3 GFLOPS: 11.68/240.37 result: MeasureResult(costs=(0.019824858333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7285661697387695, timestamp=1679480319.670046) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4700806
+ No: 4 GFLOPS: 11.96/240.37 result: MeasureResult(costs=(0.019355658166666668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.30946683883667, timestamp=1679480322.1305206) [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9389098
+ No: 5 GFLOPS: 0.00/240.37 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -513,8 +516,26 @@ 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 875, 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, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3065192
- No: 3 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, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7452442
+ No: 6 GFLOPS: 0.00/240.37 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9617960
+ No: 7 GFLOPS: 0.00/240.37 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -636,9 +657,8 @@ 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 875, 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, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9756393
- No: 4 GFLOPS: 63.61/63.61 result: MeasureResult(costs=(0.0036392384,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1150307655334473, timestamp=1679480272.8978193) [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,399155
- No: 5 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ 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, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1667464
+ No: 8 GFLOPS: 0.00/240.37 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -760,8 +780,9 @@ 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 875, 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, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4364226
- No: 6 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4411577
+ No: 9 GFLOPS: 263.35/263.35 result: MeasureResult(costs=(0.0008790775027932962,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9729106426239014, timestamp=1679480336.942195) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4752474
+ No: 10 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -883,8 +904,8 @@ 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 875, 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, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,905819
- No: 7 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4764912
+ No: 11 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1006,8 +1027,8 @@ 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 875, 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, 4, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3502828
- No: 8 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7511271
+ No: 12 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1129,8 +1150,8 @@ 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 875, 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, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4407883
- No: 9 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6211255
+ No: 13 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1252,8 +1273,8 @@ 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 875, 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, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1191008
- No: 10 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9672716
+ No: 14 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1375,8 +1396,8 @@ 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 875, 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, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8381635
- No: 11 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,636386
+ No: 15 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1498,8 +1519,8 @@ 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 875, 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, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1961907
- No: 12 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7583033
+ No: 16 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1621,8 +1642,8 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10111342
- No: 13 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5254791
+ No: 17 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1744,8 +1765,8 @@ 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 875, 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, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3321167
- No: 14 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5979400
+ No: 18 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1867,8 +1888,8 @@ 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 875, 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, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5013278
- No: 15 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9805266
+ No: 19 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1990,10 +2011,8 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10014083
- No: 16 GFLOPS: 283.04/283.04 result: MeasureResult(costs=(0.0008179004712643678,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6042275428771973, timestamp=1679480278.1020658) [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2522137
- No: 17 GFLOPS: 199.37/283.04 result: MeasureResult(costs=(0.0011611694772727273,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9948115348815918, timestamp=1679480281.3582416) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1620973
- No: 18 GFLOPS: 0.00/283.04 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9955226
+ No: 20 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2115,9 +2134,7 @@ 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 875, 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, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5978366
- No: 19 GFLOPS: 156.35/283.04 result: MeasureResult(costs=(0.0014806446666666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5363528728485107, timestamp=1679480282.2197342) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2203963
- No: 20 GFLOPS: 92.07/283.04 result: MeasureResult(costs=(0.00251453685,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9266879558563232, timestamp=1679480283.0750692) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8008761
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4778051
@@ -2172,9 +2189,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2522137
+ [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4752474
Finish loading 20 records
- Time cost of this operator: 0.001276
+ Time cost of this operator: 0.001240
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 edc2926dc9..1afbb81c2a 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
@@ -360,10 +360,10 @@ 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 315.1 98.743 (1, 2, 10, 10, 3) 2 1 [315.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.953 (1, 6, 10, 10) 1 1 [3.042]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.304 (1, 1, 10, 10, 3) 1 1 [0.97]
- Total_time - 319.112 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.6 98.741 (1, 2, 10, 10, 3) 2 1 [316.6]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.07 0.958 (1, 6, 10, 10) 1 1 [3.07]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.302 (1, 1, 10, 10, 3) 1 1 [0.968]
+ Total_time - 320.638 - - - - -
@@ -428,10 +428,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.0 97.5 (1, 6, 10, 10, 1) 2 1 [103.0]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.785 1.69 (1, 6, 10, 10) 1 1 [1.785]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.856 0.81 (1, 3, 10, 10, 1) 1 1 [0.856]
- Total_time - 105.641 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 101.7 97.356 (1, 6, 10, 10, 1) 2 1 [101.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.795 1.718 (1, 6, 10, 10) 1 1 [1.795]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 0.926 (1, 1, 10, 10, 3) 1 1 [0.967]
+ Total_time - 104.462 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.041 seconds)
+ **Total running time of the script:** ( 1 minutes 26.178 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 6cb1ff6b38..f1010271a3 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -118,7 +118,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 106MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 166MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.927 seconds)
+ **Total running time of the script:** ( 1 minutes 16.497 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
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 b88d80f6f5..31639800c8 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
@@ -217,7 +217,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp7kq46wp_/images/random'
+ '/tmp/tmpuksbrz7v/images/random'
@@ -308,7 +308,7 @@ 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: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [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]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -317,8 +317,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp7kq46wp_/images/target contains 8144 images
- /tmp/tmp7kq46wp_/images/random contains 5000 images
+ /tmp/tmpuksbrz7v/images/target contains 8144 images
+ /tmp/tmpuksbrz7v/images/random contains 5000 images
@@ -493,13 +493,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 41s - loss: 0.2246 - accuracy: 0.9236 - val_loss: 0.1052 - val_accuracy: 0.9649 - 41s/epoch - 124ms/step
+ 328/328 - 41s - loss: 0.2223 - accuracy: 0.9224 - val_loss: 0.1851 - val_accuracy: 0.9392 - 41s/epoch - 125ms/step
Epoch 2/3
- 328/328 - 35s - loss: 0.1028 - accuracy: 0.9637 - val_loss: 0.1085 - val_accuracy: 0.9664 - 35s/epoch - 106ms/step
+ 328/328 - 35s - loss: 0.1118 - accuracy: 0.9596 - val_loss: 0.1019 - val_accuracy: 0.9626 - 35s/epoch - 107ms/step
Epoch 3/3
- 328/328 - 35s - loss: 0.0732 - accuracy: 0.9721 - val_loss: 0.1114 - val_accuracy: 0.9664 - 35s/epoch - 105ms/step
+ 328/328 - 35s - loss: 0.0660 - accuracy: 0.9739 - val_loss: 0.1076 - val_accuracy: 0.9649 - 35s/epoch - 106ms/step
- <keras.callbacks.History object at 0x7f84a5364710>
+ <keras.callbacks.History object at 0x7fd37936ba10>
@@ -860,7 +860,7 @@ 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:** ( 3 minutes 49.126 seconds)
+ **Total running time of the script:** ( 3 minutes 48.717 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 46622bb7bd..d03242a7ad 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
@@ -5,20 +5,20 @@
Computation times
=================
-**06:52.937** total execution time for **how_to_work_with_microtvm** files:
+**06:57.874** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 03:49.126 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 03:48.717 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:21.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:26.178 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:16.927 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:16.497 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.301 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.155 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:07.980 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:08.512 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.561 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.816 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 6626860855..4c0b35dc0c 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
=================
-**00:36.262** total execution time for **how_to_work_with_relay** files:
+**00:37.060** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.806 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.337 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:02.856 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:02.876 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.593 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.840 | 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 |
+----------------------------------------------------------------------------------------------------+-----------+--------+
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 a70bc9278b..b92c0ea42f 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
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f80efe03830>
+ <function my_cuda_math_rule at 0x7fd11222b5f0>
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 2169fcfa32..34f6b97d9f 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:07.048** total execution time for **how_to_work_with_schedules** files:
+**00:05.884** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.132 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.959 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.406 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.438 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.622 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.613 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.611 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.600 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.129 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.128 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.063 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.062 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.055 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.054 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.029 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.030 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 0c9fc30a3a..a8bb7d3946 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
=================
-**00:31.318** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:32.426** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.312 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:32.419 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 4d1a640cda..a26742119b 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ 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 33.65s!
+ resnet18_v1 inference graph built in 35.66s!
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 e8eda5f256..f48aeecc4a 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ 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 22.21s!
+ yolov3-tiny inference graph built in 24.06s!
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 17b7bf7c53..e689f159e8 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
=================
-**01:39.874** total execution time for **topic_vta_tutorials_frontend** files:
+**01:43.706** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.713 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:52.781 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.160 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.924 | 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 67c281517a..430ac0f57f 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
=================
-**00:03.202** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.275** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.714 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.778 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.488 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.497 | 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 f40832272d..d88604bebc 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -8,7 +8,7 @@ Computation times
**00:00.845** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.434 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.438 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.410 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.407 | 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 03d19d609c..d97b3999a8 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -318,7 +318,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.659 ms
+ Execution time of this operator: 97.542 ms
@@ -434,7 +434,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 34.846 seconds)
+ **Total running time of the script:** ( 1 minutes 24.026 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 b47b5d3b85..fab5e48be1 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 1.26/1.26 result: MeasureResult(costs=(0.21357476339999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.654994010925293, timestamp=1679478656.1902423) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
- No: 2 GFLOPS: 9.00/9.00 result: MeasureResult(costs=(0.029832763999999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.107313871383667, timestamp=1679478656.9356382) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
- No: 3 GFLOPS: 12.96/12.96 result: MeasureResult(costs=(0.020711028,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7063040733337402, timestamp=1679478658.770175) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
- No: 4 GFLOPS: 9.74/12.96 result: MeasureResult(costs=(0.027567378400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6625292301177979, timestamp=1679478659.472333) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
- No: 5 GFLOPS: 11.52/12.96 result: MeasureResult(costs=(0.023292152400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6334025859832764, timestamp=1679478660.2453198) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
- No: 6 GFLOPS: 2.68/12.96 result: MeasureResult(costs=(0.100212551,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8593904972076416, timestamp=1679478663.3616052) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
- No: 7 GFLOPS: 10.36/12.96 result: MeasureResult(costs=(0.0259035974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6861972808837891, timestamp=1679478665.2850266) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
- No: 8 GFLOPS: 13.72/13.72 result: MeasureResult(costs=(0.0195708394,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5881080627441406, timestamp=1679478665.856312) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
- No: 9 GFLOPS: 3.25/13.72 result: MeasureResult(costs=(0.08261126040000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5338115692138672, timestamp=1679478667.5181794) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
- No: 10 GFLOPS: 11.74/13.72 result: MeasureResult(costs=(0.0228625504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.597022533416748, timestamp=1679478668.1488285) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
+ No: 1 GFLOPS: 10.64/10.64 result: MeasureResult(costs=(0.0252406294,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6602799892425537, timestamp=1679478690.2342584) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+ No: 2 GFLOPS: 9.91/10.64 result: MeasureResult(costs=(0.027085973800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.678652286529541, timestamp=1679478692.1526484) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+ No: 3 GFLOPS: 2.07/10.64 result: MeasureResult(costs=(0.129673222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.315542697906494, timestamp=1679478695.7194266) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 4 GFLOPS: 1.31/10.64 result: MeasureResult(costs=(0.20482821499999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.505256175994873, timestamp=1679478699.2506433) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+ No: 5 GFLOPS: 10.68/10.68 result: MeasureResult(costs=(0.0251386018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6770076751708984, timestamp=1679478700.0876095) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
+ No: 6 GFLOPS: 2.52/10.68 result: MeasureResult(costs=(0.10664173699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9691181182861328, timestamp=1679478702.0530665) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
+ No: 7 GFLOPS: 3.09/10.68 result: MeasureResult(costs=(0.086927122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6492116451263428, timestamp=1679478704.928777) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+ No: 8 GFLOPS: 10.23/10.68 result: MeasureResult(costs=(0.0262502968,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7269477844238281, timestamp=1679478705.6031437) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
+ No: 9 GFLOPS: 1.34/10.68 result: MeasureResult(costs=(0.20104186799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.417808771133423, timestamp=1679478709.1393392) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
+ No: 10 GFLOPS: 0.51/10.68 result: MeasureResult(costs=(0.5288554314,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.67240834236145, timestamp=1679478717.8649826) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 9907c319f8..866a9db3c7 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 514.2599545799976, 'median': 514.1435266999963, 'std': 1.985741545384889}
+ {'mean': 512.1068799599993, 'median': 512.0930592999969, 'std': 2.9358509438286267}
@@ -545,30 +545,29 @@ 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: 11.30/ 13.53 GFLOPS | Progress: (4/20) | 11.24 s
[Task 1/25] Current/Best: 22.84/ 22.84 GFLOPS | Progress: (8/20) | 16.08 s
[Task 1/25] Current/Best: 12.38/ 22.84 GFLOPS | Progress: (12/20) | 19.86 s
[Task 1/25] Current/Best: 6.42/ 22.84 GFLOPS | Progress: (16/20) | 24.03 s
[Task 1/25] Current/Best: 11.17/ 22.84 GFLOPS | Progress: (20/20) | 29.40 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 20.40/ 20.82 GFLOPS | Progress: (4/20) | 4.36 s
[Task 2/25] Current/Best: 20.43/ 20.82 GFLOPS | Progress: (8/20) | 5.71 s
[Task 2/25] Current/Best: 8.75/ 20.82 GFLOPS | Progress: (12/20) | 7.34 s
[Task 2/25] Current/Best: 15.94/ 20.82 GFLOPS | Progress: (16/20) | 8.81 s
[Task 2/25] Current/Best: 17.17/ 20.82 GFLOPS | Progress: (20/20) | 10.33 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 24.02/ 24.02 GFLOPS | Progress: (4/20) | 5.96 s
[Task 3/25] Current/Best: 17.92/ 24.02 GFLOPS | Progress: (8/20) | 8.10 s
[Task 3/25] Current/Best: 16.30/ 24.02 GFLOPS | Progress: (12/20) | 10.43 s
[Task 3/25] Current/Best: 20.90/ 24.02 GFLOPS | Progress: (16/20) | 13.07 s
[Task 3/25] Current/Best: 8.44/ 24.02 GFLOPS | Progress: (20/20) | 15.69 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 3.94/ 12.38 GFLOPS | Progress: (4/20) | 5.03 s
[Task 4/25] Current/Best: 12.22/ 16.94 GFLOPS | Progress: (8/20) | 7.09 s
[Task 4/25] Current/Best: 21.42/ 21.42 GFLOPS | Progress: (12/20) | 12.00 s
[Task 4/25] Current/Best: 5.05/ 21.42 GFLOPS | Progress: (16/20) | 14.37 s
[Task 4/25] Current/Best: 14.85/ 21.93 GFLOPS | Progress: (20/20) | 16.06 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 4.22/ 14.28 GFLOPS | Progress: (4/20) | 5.38 s
[Task 5/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (8/20) | 8.07 s
[Task 5/25] Current/Best: 6.34/ 19.80 GFLOPS | Progress: (12/20) | 10.45 s
[Task 5/25] Current/Best: 15.26/ 20.16 GFLOPS | Progress: (16/20) | 12.08 s
[Task 5/25] Current/Best: 2.78/ 20.16 GFLOPS | Progress: (20/20) | 14.51 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 10.26/ 17.45 GFLOPS | Progress: (4/20) | 5.20 s
[Task 6/25] Current/Best: 12.40/ 17.45 GFLOPS | Progress: (8/20) | 7.45 s
[Task 6/25] Current/Best: 3.01/ 17.45 GFLOPS | Progress: (12/20) | 12.20 s
[Task 6/25] Current/Best: 15.27/ 17.45 GFLOPS | Progress: (16/20) | 15.45 s
[Task 6/25] Current/Best: 15.92/ 17.45 GFLOPS | Progress: (20/20) | 19.53 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 19.35/ 19.35 GFLOPS | Progress: (4/20) | 5.00 s
[Task 7/25] Current/Best: 5.90/ 19.35 GFLOPS | Progress: (8/20) | 8.25 s
[Task 7/25] Current/Best: 22.12/ 22.12 GFLOPS | Progress: (12/20) | 10.16 s
[Task 7/25] Current/Best: 8.68/ 22.12 GFLOPS | Progress: (16/20) | 12.78 s
[Task 7/25] Current/Best: 3.13/ 22.12 GFLOPS | Progress: (20/20) | 15.98 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.10/ 12.04 GFLOPS | Progress: (4/20) | 8.38 s
[Task 8/25] Current/Best: 2.44/ 21.12 GFLOPS | Progress: (8/20) | 11.53 s
[Task 8/25] Current/Best: 22.06/ 22.06 GFLOPS | Progress: (12/20) | 14.12 s
[Task 8/25] Current/Best: 9.76/ 22.06 GFLOPS | Progress: (16/20) | 20.31 s
[Task 8/25] Current/Best: 2.89/ 22.06 GFLOPS | Progress: (20/20) | 23.62 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 15.58/ 15.58 GFLOPS | Progress: (4/20) | 5.14 s
[Task 9/25] Current/Best: 11.42/ 17.02 GFLOPS | Progress: (8/20) | 8.55 s
[Task 9/25] Current/Best: 15.90/ 17.02 GFLOPS | Progress: (12/20) | 10.71 s
[Task 9/25] Current/Best: 10.89/ 19.04 GFLOPS | Progress: (16/20) | 16.06 s
[Task 9/25] Current/Best: 14.22/ 19.04 GFLOPS | Progress: (20/20) | 21.81 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.02/ 18.02 GFLOPS | Progress: (4/20) | 4.83 s
[Task 10/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (8/20) | 7.81 s
[Task 10/25] Current/Best: 5.74/ 18.15 GFLOPS | Progress: (12/20) | 9.72 s
[Task 10/25] Current/Best: 12.55/ 20.01 GFLOPS | Progress: (16/20) | 11.87 s
[Task 10/25] Current/Best: 8.17/ 20.01 GFLOPS | Progress: (20/20) | 15.26 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (4/20) | 5.33 s
[Task 11/25] Current/Best: 19.07/ 21.41 GFLOPS | Progress: (8/20) | 7.33 s
[Task 11/25] Current/Best: 6.89/ 21.41 GFLOPS | Progress: (12/20) | 11.69 s
[Task 11/25] Current/Best: 18.31/ 21.41 GFLOPS | Progress: (16/20) | 13.87 s
[Task 11/25] Current/Best: 19.33/ 21.41 GFLOPS | Progress: (20/20) | 17.36 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 11.61/ 15.76 GFLOPS | Progress: (4/20) | 5.07 s
[Task 12/25] Current/Best: 11.44/ 15.76 GFLOPS | Progress: (8/20) | 9.12 s
[Task 12/25] Current/Best: 14.47/ 15.77 GFLOPS | Progress: (12/20) | 15.72 s
[Task 12/25] Current/Best: 12.68/ 15.77 GFLOPS | Progress: (16/20) | 19.42 s
[Task 12/25] Current/Best: 18.33/ 18.33 GFLOPS | Progress: (20/20) | 21.69 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 5.73/ 11.65 GFLOPS | Progress: (4/20) | 6.51 s
[Task 13/25] Current/Best: 15.23/ 19.12 GFLOPS | Progress: (8/20) | 9.27 s
[Task 13/25] Current/Best: 9.70/ 19.12 GFLOPS | Progress: (12/20) | 12.50 s
[Task 13/25] Current/Best: 15.28/ 23.20 GFLOPS | Progress: (16/20) | 14.92 s
[Task 13/25] Current/Best: 12.84/ 23.20 GFLOPS | Progress: (20/20) | 17.92 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 9.60/ 12.95 GFLOPS | Progress: (4/20) | 5.20 s
[Task 14/25] Current/Best: 9.89/ 15.08 GFLOPS | Progress: (8/20) | 9.00 s
[Task 14/25] Current/Best: 13.46/ 18.57 GFLOPS | Progress: (12/20) | 11.24 s
[Task 14/25] Current/Best: 16.27/ 18.57 GFLOPS | Progress: (16/20) | 13.34 s
[Task 14/25] Current/Best: 16.22/ 18.57 GFLOPS | Progress: (20/20) | 17.30 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 18.32/ 18.86 GFLOPS | Progress: (4/20) | 4.29 s
[Task 15/25] Current/Best: 6.03/ 19.97 GFLOPS | Progress: (8/20) | 7.03 s
[Task 15/25] Current/Best: 15.84/ 23.63 GFLOPS | Progress: (12/20) | 9.96 s
[Task 15/25] Current/Best: 8.32/ 23.63 GFLOPS | Progress: (16/20) | 17.26 s
[Task 15/25] Current/Best: 12.81/ 23.63 GFLOPS | Progress: (20/20) | 19.37 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 14.90/ 18.08 GFLOPS | Progress: (4/20) | 6.13 s
[Task 16/25] Current/Best: 15.74/ 18.08 GFLOPS | Progress: (8/20) | 8.00 s
[Task 16/25] Current/Best: 17.73/ 18.16 GFLOPS | Progress: (12/20) | 10.32 s
[Task 16/25] Current/Best: 9.73/ 18.16 GFLOPS | Progress: (16/20) | 13.47 s
[Task 16/25] Current/Best: 13.17/ 18.16 GFLOPS | Progress: (20/20)
| 16.56 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 17.35/ 18.82 GFLOPS | Progress: (4/20) | 5.35 s
[Task 17/25] Current/Best: 15.82/ 18.82 GFLOPS | Progress: (8/20) | 8.54 s
[Task 17/25] Current/Best: 17.15/ 20.89 GFLOPS | Progress: (12/20) | 10.46 s
[Task 17/25] Current/Best: 5.37/ 20.89 GFLOPS | Progress: (16/20) | 13.22 s
[Task 17/25] Current/Best: 23.70/ 23.70 GFLOPS | Progress: (20/20) | 16.04 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.94/ 11.94 GFLOPS | Progress: (4/20) | 6.98 s
[Task 18/25] Current/Best: 19.96/ 19.96 GFLOPS | Progress: (8/20) | 9.32 s
[Task 18/25] Current/Best: 10.06/ 19.96 GFLOPS | Progress: (12/20) | 13.46 s
[Task 18/25] Current/Best: 6.61/ 19.96 GFLOPS | Progress: (16/20) | 15.84 s
[Task 18/25] Current/Best: 13.72/ 19.96 GFLOPS | Progress: (20/20) | 18.95 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.31/ 21.31 GFLOPS | Progress: (4/20) | 8.62 s
[Task 19/25] Current/Best: 9.20/ 21.31 GFLOPS | Progress: (8/20) | 12.61 s
[Task 19/25] Current/Best: 17.91/ 21.31 GFLOPS | Progress: (12/20) | 14.71 s
[Task 19/25] Current/Best: 12.91/ 21.31 GFLOPS | Progress: (16/20) | 18.72 s
[Task 19/25] Current/Best: 11.91/ 21.31 GFLOPS | Progress: (20/20) | 23.72 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 2.69/ 20.31 GFLOPS | Progress: (4/20) | 5.56 s
[Task 20/25] Current/Best: 20.17/ 20.31 GFLOPS | Progress: (8/20) | 7.64 s
[Task 20/25] Current/Best: 12.80/ 20.31 GFLOPS | Progress: (12/20) | 10.04 s
[Task 20/25] Current/Best: 7.52/ 20.31 GFLOPS | Progress: (16/20) | 13.94 s
[Task 20/25] Current/Best: 9.59/ 20.31 GFLOPS | Progress: (20/20) | 17.00 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 2.72/ 15.55 GFLOPS | Progress: (4/20) | 6.05 s
[Task 21/25] Current/Best: 14.11/ 15.55 GFLOPS | Progress: (8/20) | 8.01 s
[Task 21/25] Current/Best: 15.46/ 18.54 GFLOPS | Progress: (12/20) | 10.92 s Done.
- Done.
-
[Task 21/25] Current/Best: 19.94/ 19.94 GFLOPS | Progress: (16/20) | 13.35 s
[Task 21/25] Current/Best: 15.04/ 19.94 GFLOPS | Progress: (20/20) | 16.29 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 8.64/ 20.04 GFLOPS | Progress: (4/20) | 4.86 s
[Task 22/25] Current/Best: 7.75/ 20.04 GFLOPS | Progress: (8/20) | 7.24 s
[Task 22/25] Current/Best: 12.32/ 20.04 GFLOPS | Progress: (12/20) | 9.11 s
[Task 22/25] Current/Best: 7.25/ 20.04 GFLOPS | Progress: (16/20) | 10.80 s
[Task 22/25] Current/Best: 5.26/ 20.04 GFLOPS | Progress: (20/20) | 14.47 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.42/ 10.42 GFLOPS | Progress: (4/20) | 7.69 s
[Task 23/25] Current/Best: 23.74/ 23.74 GFLOPS | Progress: (8/20) | 11.67 s
[Task 23/25] Current/Best: 10.24/ 23.74 GFLOPS | Progress: (12/20) | 14.75 s
[Task 23/25] Current/Best: 11.89/ 23.74 GFLOPS | Progress: (16/20) | 18.06 s
[Task 23/25] Current/Best: 12.09/ 23.74 GFLOPS | Progress: (20/20) | 21.18 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (4/20) | 12.84 s
[Task 24/25] Current/Best: 1.09/ 3.81 GFLOPS | Progress: (8/20) | 25.51 s
[Task 24/25] Current/Best: 3.42/ 4.03 GFLOPS | Progress: (12/20) | 38.12 s
[Task 24/25] Current/Best: 1.45/ 4.03 GFLOPS | Progress: (16/20) | 50.76 s
[Task 24/25] Current/Best: 1.55/ 4.03 GFLOPS | Progress: (20/20) | 61.76 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 8.88/ 8.88 GFLOPS | Progress: (4/20) | 14.95 s
[Task 25/25] Current/Best: 1.53/ 8.88 GFLOPS | Progress: (8/20) | 27.53 s
[Task 25/25] Current/Best: 1.55/ 8.88 GFLOPS | Progress: (12/20) | 30.68 s
[Task 25/25] Current/Best: 9.36/ 9.36 GFLOPS | Progress: (16/20) | 41.34 s
[Task 25/25] Current/Best: 1.55/ 9.36 GFLOPS | Progress: (20/20) | 52.30 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 18.35/ 19.55 GFLOPS | Progress: (4/20) | 10.68 s
[Task 1/25] Current/Best: 22.13/ 22.13 GFLOPS | Progress: (8/20) | 17.93 s
[Task 1/25] Current/Best: 19.09/ 22.13 GFLOPS | Progress: (12/20) | 23.31 s
[Task 1/25] Current/Best: 6.28/ 23.32 GFLOPS | Progress: (16/20) | 26.14 s
[Task 1/25] Current/Best: 14.18/ 23.32 GFLOPS | Progress: (20/20) | 28.72 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.07/ 15.55 GFLOPS | Progress: (4/20) | 4.46 s
[Task 2/25] Current/Best: 18.97/ 18.97 GFLOPS | Progress: (8/20) | 6.42 s
[Task 2/25] Current/Best: 16.89/ 20.73 GFLOPS | Progress: (12/20) | 7.85 s
[Task 2/25] Current/Best: 8.28/ 20.73 GFLOPS | Progress: (16/20) | 10.79 s
[Task 2/25] Current/Best: 5.78/ 20.73 GFLOPS | Progress: (20/20) | 12.40 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 17.98/ 18.16 GFLOPS | Progress: (4/20) | 6.25 s
[Task 3/25] Current/Best: 12.72/ 20.96 GFLOPS | Progress: (8/20) | 8.61 s
[Task 3/25] Current/Best: 7.75/ 20.96 GFLOPS | Progress: (12/20) | 11.89 s
[Task 3/25] Current/Best: 18.43/ 20.96 GFLOPS | Progress: (16/20) | 14.35 s
[Task 3/25] Current/Best: 19.21/ 20.96 GFLOPS | Progress: (20/20) | 17.67 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.63/ 19.56 GFLOPS | Progress: (4/20) | 5.72 s
[Task 4/25] Current/Best: 11.55/ 19.56 GFLOPS | Progress: (8/20) | 10.61 s
[Task 4/25] Current/Best: 4.93/ 19.56 GFLOPS | Progress: (12/20) | 15.52 s
[Task 4/25] Current/Best: 6.48/ 19.56 GFLOPS | Progress: (16/20) | 17.97 s
[Task 4/25] Current/Best: 5.62/ 19.56 GFLOPS | Progress: (20/20) | 20.40 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 10.02/ 15.96 GFLOPS | Progress: (4/20) | 5.48 s
[Task 5/25] Current/Best: 11.41/ 15.96 GFLOPS | Progress: (8/20) | 8.16 s
[Task 5/25] Current/Best: 12.78/ 15.96 GFLOPS | Progress: (12/20) | 11.03 s
[Task 5/25] Current/Best: 13.05/ 17.99 GFLOPS | Progress: (16/20) | 13.08 s
[Task 5/25] Current/Best: 14.80/ 17.99 GFLOPS | Progress: (20/20) | 15.29 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.84/ 19.49 GFLOPS | Progress: (4/20) | 5.17 s
[Task 6/25] Current/Best: 12.95/ 19.49 GFLOPS | Progress: (8/20) | 7.52 s
[Task 6/25] Current/Best: 6.08/ 19.49 GFLOPS | Progress: (12/20) | 10.92 s
[Task 6/25] Current/Best: 13.64/ 19.49 GFLOPS | Progress: (16/20) | 13.91 s
[Task 6/25] Current/Best: 14.31/ 19.49 GFLOPS | Progress: (20/20) | 17.29 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 3.06/ 18.50 GFLOPS | Progress: (4/20) | 5.29 s
[Task 7/25] Current/Best: 5.76/ 18.50 GFLOPS | Progress: (8/20) | 8.06 s
[Task 7/25] Current/Best: 9.60/ 18.50 GFLOPS | Progress: (12/20) | 11.09 s
[Task 7/25] Current/Best: 18.01/ 18.50 GFLOPS | Progress: (16/20) | 13.33 s
[Task 7/25] Current/Best: 12.58/ 18.50 GFLOPS | Progress: (20/20) | 16.03 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.98/ 16.88 GFLOPS | Progress: (4/20) | 5.09 s
[Task 8/25] Current/Best: 10.58/ 16.88 GFLOPS | Progress: (8/20) | 8.04 s
[Task 8/25] Current/Best: 2.93/ 16.88 GFLOPS | Progress: (12/20) | 15.22 s
[Task 8/25] Current/Best: 17.79/ 17.79 GFLOPS | Progress: (16/20) | 18.34 s
[Task 8/25] Current/Best: 10.44/ 17.79 GFLOPS | Progress: (20/20) | 21.69 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 8.84/ 17.45 GFLOPS | Progress: (4/20) | 7.46 s
[Task 9/25] Current/Best: 4.82/ 17.45 GFLOPS | Progress: (8/20) | 15.45 s
[Task 9/25] Current/Best: 6.03/ 17.45 GFLOPS | Progress: (12/20) | 23.85 s
[Task 9/25] Current/Best: 10.20/ 17.45 GFLOPS | Progress: (16/20) | 27.59 s
[Task 9/25] Current/Best: 19.69/ 19.69 GFLOPS | Progress: (20/20) | 29.33 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 15.08/ 16.05 GFLOPS | Progress: (4/20) | 4.36 s
[Task 10/25] Current/Best: 10.87/ 17.31 GFLOPS | Progress: (8/20) | 6.08 s
[Task 10/25] Current/Best: 14.95/ 18.78 GFLOPS | Progress: (12/20) | 8.12 s
[Task 10/25] Current/Best: 12.79/ 22.75 GFLOPS | Progress: (16/20) | 10.40 s
[Task 10/25] Current/Best: 4.81/ 22.75 GFLOPS | Progress: (20/20) | 12.10 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 6.20/ 14.92 GFLOPS | Progress: (4/20) | 5.64 s
[Task 11/25] Current/Best: 12.16/ 22.25 GFLOPS | Progress: (8/20) | 8.31 s
[Task 11/25] Current/Best: 3.10/ 22.25 GFLOPS | Progress: (12/20) | 12.12 s
[Task 11/25] Current/Best: 20.40/ 23.24 GFLOPS | Progress: (16/20) | 14.57 s
[Task 11/25] Current/Best: 16.05/ 23.24 GFLOPS | Progress: (20/20) | 16.71 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.35/ 13.70 GFLOPS | Progress: (4/20) | 7.59 s
[Task 12/25] Current/Best: 14.62/ 20.51 GFLOPS | Progress: (8/20) | 9.75 s
[Task 12/25] Current/Best: 7.79/ 20.51 GFLOPS | Progress: (12/20) | 13.58 s
[Task 12/25] Current/Best: 10.16/ 20.51 GFLOPS | Progress: (16/20) | 18.73 s
[Task 12/25] Current/Best: 11.29/ 20.51 GFLOPS | Progress: (20/20) | 22.19 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 4.58/ 16.86 GFLOPS | Progress: (4/20) | 6.06 s
[Task 13/25] Current/Best: 11.62/ 16.86 GFLOPS | Progress: (8/20) | 10.08 s
[Task 13/25] Current/Best: 16.46/ 16.86 GFLOPS | Progress: (12/20) | 13.93 s
[Task 13/25] Current/Best: 7.93/ 20.34 GFLOPS | Progress: (16/20) | 17.35 s
[Task 13/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (20/20) | 20.48 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.78/ 13.78 GFLOPS | Progress: (4/20) | 4.60 s
[Task 14/25] Current/Best: 12.64/ 13.78 GFLOPS | Progress: (8/20) | 9.21 s
[Task 14/25] Current/Best: 8.19/ 17.70 GFLOPS | Progress: (12/20) | 11.50 s
[Task 14/25] Current/Best: 9.19/ 17.70 GFLOPS | Progress: (16/20) | 15.46 s
[Task 14/25] Current/Best: 21.44/ 21.44 GFLOPS | Progress: (20/20) | 20.16 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 14.26/ 19.72 GFLOPS | Progress: (4/20) | 5.44 s
[Task 15/25] Current/Best: 23.12/ 23.12 GFLOPS | Progress: (8/20) | 8.36 s
[Task 15/25] Current/Best: 19.92/ 23.12 GFLOPS | Progress: (12/20) | 11.75 s
[Task 15/25] Current/Best: 10.15/ 23.12 GFLOPS | Progress: (16/20) | 13.64 s
[Task 15/25] Current/Best: 13.16/ 23.12 GFLOPS | Progress: (20/20
) | 15.88 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 5.82/ 14.68 GFLOPS | Progress: (4/20) | 4.68 s
[Task 16/25] Current/Best: 13.21/ 14.68 GFLOPS | Progress: (8/20) | 8.00 s
[Task 16/25] Current/Best: 18.55/ 18.55 GFLOPS | Progress: (12/20) | 9.78 s
[Task 16/25] Current/Best: 14.12/ 18.55 GFLOPS | Progress: (16/20) | 12.52 s
[Task 16/25] Current/Best: 11.26/ 18.55 GFLOPS | Progress: (20/20) | 16.14 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.28/ 20.42 GFLOPS | Progress: (4/20) | 5.03 s
[Task 17/25] Current/Best: 16.62/ 20.42 GFLOPS | Progress: (8/20) | 7.34 s
[Task 17/25] Current/Best: 12.46/ 20.42 GFLOPS | Progress: (12/20) | 10.34 s
[Task 17/25] Current/Best: 7.64/ 20.42 GFLOPS | Progress: (16/20) | 13.17 s
[Task 17/25] Current/Best: 20.36/ 20.42 GFLOPS | Progress: (20/20) | 16.35 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 17.86/ 19.00 GFLOPS | Progress: (4/20) | 4.53 s
[Task 18/25] Current/Best: 18.33/ 21.06 GFLOPS | Progress: (8/20) | 8.01 s
[Task 18/25] Current/Best: 12.09/ 21.06 GFLOPS | Progress: (12/20) | 10.91 s
[Task 18/25] Current/Best: 14.74/ 21.06 GFLOPS | Progress: (16/20) | 13.30 s
[Task 18/25] Current/Best: 18.47/ 21.06 GFLOPS | Progress: (20/20) | 15.44 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (4/20) | 5.75 s
[Task 19/25] Current/Best: 11.05/ 19.96 GFLOPS | Progress: (8/20) | 8.79 s
[Task 19/25] Current/Best: 18.73/ 19.96 GFLOPS | Progress: (12/20) | 11.48 s
[Task 19/25] Current/Best: 10.46/ 21.35 GFLOPS | Progress: (16/20) | 16.78 s
[Task 19/25] Current/Best: 8.87/ 21.35 GFLOPS | Progress: (20/20) | 21.20 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 12.95/ 12.95 GFLOPS | Progress: (4/20) | 5.51 s
[Task 20/25] Current/Best: 11.51/ 17.19 GFLOPS | Progress: (8/20) | 11.85 s
[Task 20/25] Current/Best: 14.40/ 17.19 GFLOPS | Progress: (12/20) | 13.28 s
[Task 20/25] Current/Best: 14.41/ 18.21 GFLOPS | Progress: (16/20) | 17.44 s
[Task 20/25] Current/Best: 9.54/ 18.21 GFLOPS | Progress: (20/20) | 19.63 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 21/25] Current/Best: 16.47/ 19.56 GFLOPS | Progress: (4/20) | 5.19 s
[Task 21/25] Current/Best: 14.75/ 19.56 GFLOPS | Progress: (8/20) | 8.17 s
[Task 21/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (12/20) | 10.02 s
[Task 21/25] Current/Best: 9.65/ 20.06 GFLOPS | Progress: (16/20) | 12.80 s
[Task 21/25] Current/Best: 10.12/ 20.06 GFLOPS | Progress: (20/20) | 16.02 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 7.98/ 19.96 GFLOPS | Progress: (4/20) | 4.70 s
[Task 22/25] Current/Best: 4.92/ 19.96 GFLOPS | Progress: (8/20) | 8.05 s
[Task 22/25] Current/Best: 16.80/ 19.96 GFLOPS | Progress: (12/20) | 9.64 s
[Task 22/25] Current/Best: 19.03/ 19.96 GFLOPS | Progress: (16/20) | 11.57 s
[Task 22/25] Current/Best: 7.67/ 19.96 GFLOPS | Progress: (20/20) | 15.04 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 19.78/ 19.90 GFLOPS | Progress: (4/20) | 4.99 s
[Task 23/25] Current/Best: 10.45/ 19.90 GFLOPS | Progress: (8/20) | 9.37 s
[Task 23/25] Current/Best: 1.55/ 19.90 GFLOPS | Progress: (12/20) | 14.80 s
[Task 23/25] Current/Best: 14.69/ 20.54 GFLOPS | Progress: (16/20) | 17.00 s
[Task 23/25] Current/Best: 12.43/ 20.54 GFLOPS | Progress: (20/20) | 19.74 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.50/ 4.88 GFLOPS | Progress: (4/20) | 13.78 s
[Task 24/25] Current/Best: 3.41/ 4.88 GFLOPS | Progress: (8/20) | 26.24 s
[Task 24/25] Current/Best: 6.63/ 10.91 GFLOPS | Progress: (12/20) | 28.83 s
[Task 24/25] Current/Best: 7.18/ 10.91 GFLOPS | Progress: (16/20) | 31.05 s
[Task 24/25] Current/Best: 2.82/ 10.91 GFLOPS | Progress: (20/20) | 42.01 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 8.78/ 8.78 GFLOPS | Progress: (4/20) | 14.88 s
[Task 25/25] Current/Best: 4.18/ 8.78 GFLOPS | Progress: (8/20) | 26.79 s
[Task 25/25] Current/Best: 2.98/ 8.78 GFLOPS | Progress: (12/20) | 37.78 s
[Task 25/25] Current/Best: 1.42/ 8.78 GFLOPS | Progress: (16/20) | 46.94 s
[Task 25/25] Current/Best: 1.54/ 8.78 GFLOPS | Progress: (20/20) | 57.89 s
@@ -664,8 +663,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621102
- class='n02123159 tiger cat' with probability=0.356379
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -722,8 +721,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 402.02047891000575, 'median': 401.28876339999806, 'std': 3.301314593790155}
- unoptimized: {'mean': 514.2599545799976, 'median': 514.1435266999963, 'std': 1.985741545384889}
+ optimized: {'mean': 427.58227047000446, 'median': 427.03722730001346, 'std': 2.9315160685878006}
+ unoptimized: {'mean': 512.1068799599993, 'median': 512.0930592999969, 'std': 2.9358509438286267}
@@ -746,7 +745,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 41.810 seconds)
+ **Total running time of the script:** ( 12 minutes 34.455 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 f85df1fc73..4dcd192771 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.374e-07 secs/op
+ 1.242e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index a7e3fab603..c3a92fdf08 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -270,7 +270,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x25288c80)), stage(b, placeholder(b, 0xac1bec0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
+ [stage(a, placeholder(a, 0x228231e0)), stage(b, placeholder(b, 0x83aa7f0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 7940fbaafe..679947cd4a 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**16:19.279** total execution time for **tutorial** files:
+**16:13.386** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:41.810 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:34.455 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:34.846 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:24.026 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.262 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.178 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.515 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.611 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:22.444 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:34.658 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.372 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.454 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.855 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.842 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.176 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.163 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 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 6fddbb7586..b446e3ad10 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -285,7 +285,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000007
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000006
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.207910000237461e-06 1.0
- naive 6.725399999999999e-06 0.8193803294389714
- parallel 7.9832e-06 0.9726227504649831
- vector 2.45207e-05 2.9874474743619994
+ numpy 7.482219998564687e-06 1.0
+ naive 6.641e-06 0.8875708013495917
+ parallel 6.042800000000001e-06 0.8076212676397099
+ vector 2.4598000000000004e-05 3.2875269645531184
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017925
+ Numpy running time: 0.018556
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.441236
+ none: 3.427779
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.300444
+ blocking: 0.295800
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.334547
+ vectorization: 0.336362
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1230,7 +1230,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.114626
+ loop permutation: 0.113505
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1321,7 +1321,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108260
+ array packing: 0.107278
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110493
+ block caching: 0.110022
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146488
+ parallelization: 0.145588
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1548,13 +1548,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4412356548999994 1.0
- blocking 0.3004442279 0.08730707746567586
- vectorization 0.33454658309999996 0.09721699315292075
- loop permutation 0.1146258668 0.033309508064867176
- array packing 0.1082601003 0.03145965901691379
- block caching 0.11049327 0.03210860315325045
- parallelization 0.1464880269 0.042568438081656716
+ none 3.4277789188 1.0
+ blocking 0.2957996004 0.08629483038642229
+ vectorization 0.33636178299999997 0.09812820224641378
+ loop permutation 0.11350530429999998 0.03311336786554952
+ array packing 0.1072782304 0.03129671806183931
+ block caching 0.110022023 0.032097175928287876
+ parallelization 0.1455881197 0.04247301916162306
@@ -1596,7 +1596,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.262 seconds)
+ **Total running time of the script:** ( 1 minutes 1.178 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 5520f14865..a2225c73bd 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-0c2dd472864dddf910a27f7ef8575d15f8146a85
+c7970ddd79a1e6bbf5e07ab2c515ec4991242ef7
diff --git a/docs/genindex.html b/docs/genindex.html
index d537f68eb1..4249f39e9a 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -4779,6 +4779,8 @@
</li>
</ul></li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.UnrollLoop">UnrollLoop() (in module tvm.tir.transform)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.Schedule.unsafe_set_dtype">unsafe_set_dtype() (tvm.tir.Schedule method)</a>
</li>
<li><a href="reference/api/python/micro.html#tvm.micro.UnsupportedInModelLibraryFormatError">UnsupportedInModelLibraryFormatError</a>
</li>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 92bbed9ad9..ed83f32f57 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -590,7 +590,7 @@ 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 18.041 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.499 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 72ba789c86..d45753be8c 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -444,7 +444,7 @@
<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.zip2bfba95b-33ca-4d8e-a98f-ccfd04165508 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.zip49313ea3-fb03-47d7-9a25-3b1593e9dd18 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 a9e8ee7006..4fb6c7aa7c 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -454,11 +454,9 @@ 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, 63.2MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 60.6MB/s]
- 65%|######4 | 26.8M/41.5M [00:00<00:00, 80.6MB/s]
- 85%|########5 | 35.4M/41.5M [00:00<00:00, 84.0MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 82.3MB/s]
+ 38%|###7 | 15.8M/41.5M [00:00<00:00, 165MB/s]
+ 76%|#######5 | 31.5M/41.5M [00:00<00:00, 120MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 92.5MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 82654b789b..3e4916ead7 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -437,9 +437,10 @@ be unstable.</p>
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]
- 27%|##7 | 12.1M/44.7M [00:00<00:00, 127MB/s]
- 54%|#####4 | 24.2M/44.7M [00:00<00:00, 108MB/s]
- 78%|#######7 | 34.7M/44.7M [00:00<00:00, 106MB/s]
+ 23%|##3 | 10.4M/44.7M [00:00<00:00, 109MB/s]
+ 49%|####8 | 21.7M/44.7M [00:00<00:00, 114MB/s]
+ 73%|#######2 | 32.5M/44.7M [00:00<00:00, 106MB/s]
+ 96%|#########5| 42.7M/44.7M [00:00<00:00, 105MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 4a6b181c15..92f646052f 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -657,7 +657,7 @@ 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 30.355 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.769 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 308b4bed10..c81fcf9e85 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>06:43.278</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:34.582</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:30.355</p></td>
+<td><p>01:29.769</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:18.041</p></td>
+<td><p>01:14.499</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>00:55.973</p></td>
+<td><p>00:54.993</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>00:37.531</p></td>
+<td><p>00:37.144</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>00:32.077</p></td>
+<td><p>00:31.072</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:30.209</p></td>
+<td><p>00:29.588</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:27.507</p></td>
+<td><p>00:26.603</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>00:26.233</p></td>
+<td><p>00:26.270</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>00:22.689</p></td>
+<td><p>00:22.044</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>00:02.663</p></td>
+<td><p>00:02.600</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 7a259490c4..a4989dbb31 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -799,7 +799,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2537.5753 2536.9458 2541.9001 2535.6260 1.7455
+ 2633.5339 2632.5954 2636.6337 2631.3362 1.8132
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
index 578353c412..da72e719e7 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
@@ -443,24 +443,25 @@ to run this tutorial with a real device over rpc.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
8192/102967424 [..............................] - ETA: 0s
- 8028160/102967424 [=>............................] - ETA: 0s
- 13099008/102967424 [==>...........................] - ETA: 0s
- 16769024/102967424 [===>..........................] - ETA: 0s
- 25960448/102967424 [======>.......................] - ETA: 0s
- 27353088/102967424 [======>.......................] - ETA: 0s
- 36700160/102967424 [=========>....................] - ETA: 0s
- 41746432/102967424 [===========>..................] - ETA: 0s
- 46751744/102967424 [============>.................] - ETA: 0s
- 51724288/102967424 [==============>...............] - ETA: 0s
- 56696832/102967424 [===============>..............] - ETA: 0s
- 61841408/102967424 [=================>............] - ETA: 0s
- 66813952/102967424 [==================>...........] - ETA: 0s
- 71811072/102967424 [===================>..........] - ETA: 0s
- 76816384/102967424 [=====================>........] - ETA: 0s
- 81895424/102967424 [======================>.......] - ETA: 0s
- 86900736/102967424 [========================>.....] - ETA: 0s
- 91996160/102967424 [=========================>....] - ETA: 0s
- 94461952/102967424 [==========================>...] - ETA: 0s
+ 8781824/102967424 [=>............................] - ETA: 0s
+ 14123008/102967424 [===>..........................] - ETA: 0s
+ 19128320/102967424 [====>.........................] - ETA: 0s
+ 24190976/102967424 [======>.......................] - ETA: 0s
+ 29106176/102967424 [=======>......................] - ETA: 0s
+ 33546240/102967424 [========>.....................] - ETA: 0s
+ 39165952/102967424 [==========>...................] - ETA: 0s
+ 44228608/102967424 [===========>..................] - ETA: 0s
+ 49201152/102967424 [=============>................] - ETA: 0s
+ 54231040/102967424 [==============>...............] - ETA: 0s
+ 58851328/102967424 [================>.............] - ETA: 0s
+ 64323584/102967424 [=================>............] - ETA: 0s
+ 69328896/102967424 [===================>..........] - ETA: 0s
+ 74326016/102967424 [====================>.........] - ETA: 0s
+ 79405056/102967424 [======================>.......] - ETA: 0s
+ 83877888/102967424 [=======================>......] - ETA: 0s
+ 91701248/102967424 [=========================>....] - ETA: 0s
+ 96755712/102967424 [===========================>..] - ETA: 0s
+101720064/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
</pre></div>
</div>
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 be86a56b54..75b9221d87 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -667,7 +667,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9343 15.8414 16.5317 15.4561 0.4044
+ 15.7434 15.5668 16.3996 15.4081 0.3556
</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 4607439335..5f997cef7f 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -459,20 +459,21 @@ be unstable.</p>
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]
- 9%|9 | 16.0M/170M [00:00<00:01, 124MB/s]
- 16%|#6 | 27.8M/170M [00:00<00:01, 103MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:01, 103MB/s]
- 29%|##9 | 49.8M/170M [00:00<00:01, 96.5MB/s]
- 35%|###4 | 59.0M/170M [00:00<00:01, 86.2MB/s]
- 41%|#### | 69.1M/170M [00:00<00:01, 91.9MB/s]
- 47%|####7 | 80.1M/170M [00:00<00:00, 95.6MB/s]
- 56%|#####6 | 95.1M/170M [00:00<00:00, 113MB/s]
- 63%|######2 | 106M/170M [00:01<00:00, 98.3MB/s]
- 72%|#######2 | 123M/170M [00:01<00:00, 118MB/s]
- 79%|#######9 | 135M/170M [00:01<00:00, 115MB/s]
- 86%|########6 | 146M/170M [00:01<00:00, 94.7MB/s]
- 94%|#########4| 160M/170M [00:01<00:00, 108MB/s]
-100%|##########| 170M/170M [00:01<00:00, 101MB/s]
+ 9%|8 | 14.8M/170M [00:00<00:01, 154MB/s]
+ 17%|#7 | 29.5M/170M [00:00<00:01, 117MB/s]
+ 24%|##4 | 41.2M/170M [00:00<00:01, 85.0MB/s]
+ 32%|###2 | 54.7M/170M [00:00<00:01, 101MB/s]
+ 40%|#### | 68.0M/170M [00:00<00:00, 112MB/s]
+ 47%|####6 | 79.6M/170M [00:00<00:00, 108MB/s]
+ 53%|#####3 | 90.5M/170M [00:00<00:00, 102MB/s]
+ 59%|#####9 | 101M/170M [00:01<00:00, 96.6MB/s]
+ 66%|######5 | 112M/170M [00:01<00:00, 102MB/s]
+ 72%|#######2 | 123M/170M [00:01<00:00, 106MB/s]
+ 78%|#######8 | 133M/170M [00:01<00:00, 103MB/s]
+ 84%|########4 | 143M/170M [00:01<00:00, 103MB/s]
+ 90%|######### | 153M/170M [00:01<00:00, 102MB/s]
+ 96%|#########5| 163M/170M [00:01<00:00, 91.7MB/s]
+100%|##########| 170M/170M [00:01<00:00, 103MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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:124: 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=& [...]
@@ -570,7 +571,7 @@ 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 31.442 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 34.974 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 bbf969f82e..14686822ab 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -500,7 +500,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 165MB/s]
+ 97%|#########6| 13.1M/13.6M [00:00<00:00, 137MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 134MB/s]
</pre></div>
</div>
</div>
@@ -591,7 +592,7 @@ 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)
- 90.0796 89.9686 94.8404 89.7732 0.5329
+ 90.7131 90.5405 100.1469 90.0935 1.1737
</pre></div>
</div>
<div class="admonition note">
@@ -630,7 +631,7 @@ 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 16.009 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.198 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 2094adbd0c..9d21fc5f66 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -585,7 +585,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.8698 119.0240 120.6894 117.1571 1.0432
+ 121.0229 121.0042 125.9077 120.1047 0.6011
</pre></div>
</div>
<div class="admonition note">
@@ -613,7 +613,7 @@ 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 36.447 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 38.451 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 4ab7e1ef43..329042d9af 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -526,7 +526,7 @@ 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 27.191 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.408 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 e3893bd429..d4b7e15387 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -468,24 +468,25 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 1%| | 1290/132723 [00:00<00:10, 12856.33KB/s]
- 3%|3 | 4431/132723 [00:00<00:05, 23750.83KB/s]
- 9%|8 | 11598/132723 [00:00<00:02, 45610.37KB/s]
- 15%|#5 | 19965/132723 [00:00<00:01, 60623.44KB/s]
- 21%|##1 | 28481/132723 [00:00<00:01, 69464.55KB/s]
- 28%|##7 | 37009/132723 [00:00<00:01, 74835.88KB/s]
- 34%|###4 | 45589/132723 [00:00<00:01, 78417.04KB/s]
- 41%|#### | 54099/132723 [00:00<00:00, 80542.81KB/s]
- 47%|####7 | 62751/132723 [00:00<00:00, 82407.76KB/s]
- 54%|#####3 | 71407/132723 [00:01<00:00, 83687.72KB/s]
- 60%|###### | 79991/132723 [00:01<00:00, 84344.23KB/s]
- 67%|######6 | 88518/132723 [00:01<00:00, 84624.02KB/s]
- 73%|#######3 | 97126/132723 [00:01<00:00, 85063.11KB/s]
- 80%|#######9 | 105750/132723 [00:01<00:00, 85416.07KB/s]
- 86%|########6 | 114376/132723 [00:01<00:00, 85667.63KB/s]
- 93%|#########2| 122986/132723 [00:01<00:00, 85796.13KB/s]
- 99%|#########9| 131566/132723 [00:01<00:00, 85640.52KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 77310.60KB/s]
+ 1%| | 1248/132723 [00:00<00:10, 12478.76KB/s]
+ 3%|2 | 3964/132723 [00:00<00:06, 21113.97KB/s]
+ 7%|7 | 9818/132723 [00:00<00:03, 38201.63KB/s]
+ 13%|#3 | 17794/132723 [00:00<00:02, 54605.70KB/s]
+ 19%|#9 | 25817/132723 [00:00<00:01, 63840.41KB/s]
+ 26%|##5 | 33886/132723 [00:00<00:01, 69567.18KB/s]
+ 32%|###1 | 41937/132723 [00:00<00:01, 73141.67KB/s]
+ 38%|###7 | 49993/132723 [00:00<00:01, 75498.80KB/s]
+ 44%|####3 | 58114/132723 [00:00<00:00, 77283.15KB/s]
+ 50%|####9 | 66281/132723 [00:01<00:00, 78633.05KB/s]
+ 56%|#####6 | 74361/132723 [00:01<00:00, 79285.91KB/s]
+ 62%|######2 | 82488/132723 [00:01<00:00, 79887.63KB/s]
+ 68%|######8 | 90625/132723 [00:01<00:00, 80331.27KB/s]
+ 74%|#######4 | 98785/132723 [00:01<00:00, 80708.59KB/s]
+ 81%|######## | 106923/132723 [00:01<00:00, 80909.46KB/s]
+ 87%|########6 | 115044/132723 [00:01<00:00, 80997.32KB/s]
+ 93%|#########2| 123165/132723 [00:01<00:00, 81059.43KB/s]
+ 99%|#########8| 131316/132723 [00:01<00:00, 81193.32KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 72945.48KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -524,7 +525,7 @@ 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> ( 3 minutes 49.127 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> ( 3 minutes 58.651 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 f98c420e52..69e3b96a59 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>16:05.175</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>16:16.493</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><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>03:49.127</p></td>
+<td><p>03:58.651</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>03:31.442</p></td>
+<td><p>03:34.974</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>02:36.447</p></td>
+<td><p>02:38.451</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>01:27.191</p></td>
+<td><p>01:22.408</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>01:16.009</p></td>
+<td><p>01:16.198</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno™</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:54.568</p></td>
+<td><p>00:55.318</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_adreno_tvmc.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-tvmc-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno™ with tvmc Interface</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno_tvmc.py</span></code>)</p></td>
-<td><p>00:50.899</p></td>
+<td><p>00:50.645</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>00:42.435</p></td>
+<td><p>00:42.791</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>00:28.691</p></td>
+<td><p>00:28.743</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>00:28.360</p></td>
+<td><p>00:28.309</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 84a62f31aa..a3990c85cd 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -624,7 +624,7 @@ 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.zip6ff600c0-da71-4dbf-bfd3-84804c390e08 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.zip71c6cead-917c-423a-81ab-efebafaddae3 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 7ba85b65a5..64da2d614b 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:53.519</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:57.556</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:49.800</p></td>
+<td><p>00:53.530</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>00:02.676</p></td>
+<td><p>00:02.889</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>00:01.037</p></td>
+<td><p>00:01.130</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 3aea054f59..d156b59d6d 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -531,10 +531,10 @@ 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: 22172us [22172us] (48.81%; 48.81%)
-FoldScaleAxis: 23250us [6us] (51.19%; 51.19%)
- FoldConstant: 23244us [1685us] (51.17%; 99.97%)
- InferType: 21560us [21560us] (47.47%; 92.75%)
+InferType: 22850us [22850us] (48.68%; 48.68%)
+FoldScaleAxis: 24087us [9us] (51.32%; 51.32%)
+ FoldConstant: 24078us [1740us] (51.30%; 99.96%)
+ InferType: 22338us [22338us] (47.59%; 92.77%)
</pre></div>
</div>
</div>
@@ -556,10 +556,10 @@ 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: 21499us [21499us] (48.32%; 48.32%)
-FoldScaleAxis: 22992us [5us] (51.68%; 51.68%)
- FoldConstant: 22987us [1635us] (51.67%; 99.98%)
- InferType: 21352us [21352us] (47.99%; 92.89%)
+InferType: 22513us [22513us] (48.37%; 48.37%)
+FoldScaleAxis: 24031us [8us] (51.63%; 51.63%)
+ FoldConstant: 24023us [1768us] (51.61%; 99.97%)
+ InferType: 22255us [22255us] (47.81%; 92.64%)
</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 5ef30220db..00e0ed5254 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -580,7 +580,7 @@ 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: 52.217887 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 53.653087 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 15209bdf26..dcccc987af 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -862,7 +862,7 @@ 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: 12.246758 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.069520 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 8ddf40de56..8818b4e187 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -477,8 +477,8 @@ 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: 0.018414
-Baseline: 3.343532
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018164
+Baseline: 3.435242
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -537,7 +537,7 @@ 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: 0.299235
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.291741
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ 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: 0.333744
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.337721
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -649,7 +649,7 @@ 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: 0.119433
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120061
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -726,7 +726,7 @@ 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: 0.110272
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109663
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -804,7 +804,7 @@ 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: 0.111860
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111426
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -884,7 +884,7 @@ class Module:
<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: 0.147597
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146630
</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 3db0324a84..0e5095b1f7 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:35.301</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.377</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</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>00:32.209</p></td>
+<td><p>00:32.395</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>00:01.912</p></td>
+<td><p>00:01.831</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>00:01.181</p></td>
+<td><p>00:01.151</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 1ac091d4c7..2815cbfaed 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>10:07.542</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>10:11.975</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -354,27 +354,27 @@
</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>06:14.710</p></td>
+<td><p>06:14.017</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>01:42.353</p></td>
+<td><p>01:46.369</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>01:10.615</p></td>
+<td><p>01:11.970</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>00:32.500</p></td>
+<td><p>00:32.158</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:13.964</p></td>
+<td><p>00:14.069</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:13.400</p></td>
+<td><p>00:13.392</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 545fb07e87..19748fac1b 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
@@ -510,117 +510,346 @@ class Module:
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- blockIdx_x = T.launch_thread("blockIdx.x", 56)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([84], "float32", "shared")
- kernel_shared = T.allocate([768], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 32)
- conv2d_nchw_1 = T.Buffer((49,), data=conv2d_nchw, scope="local", align=16)
+ blockIdx_x = T.launch_thread("blockIdx.x", 32)
+ conv2d_nchw = T.allocate([16], "float32", "local")
+ pad_temp_shared = T.allocate([1296], "float32", "shared")
+ kernel_shared = T.allocate([2304], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 49)
+ conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[6] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
+ conv2d_nchw_1[14] = T.float32(0)
+ conv2d_nchw_1[1] = T.float32(0)
+ conv2d_nchw_1[3] = T.float32(0)
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(128, 3):
- cse_var_4: T.int32 = rc_outer_outer * 196
- cse_var_3: T.int32 = ry_outer_outer * 7
- cse_var_2: T.int32 = rc_outer_outer * 36
- cse_var_1: T.int32 = ry_outer_outer * 3
+ conv2d_nchw_1[15] = T.float32(0)
+ for rc_outer_outer in range(32):
+ cse_var_2: T.int32 = rc_outer_outer * 784
+ cse_var_1: T.int32 = rc_outer_outer * 144
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((84,), data=pad_temp_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((1296,), data=pad_temp_shared, scope="shared")
data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 32):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 21 // 3 + ry_outer_outer and threadIdx_x_1 % 21 // 3 + ry_outer_outer < 8 and 1 <= blockIdx_x % 7 + threadIdx_x_1 % 3 and blockIdx_x % 7 + threadIdx_x_1 % 3 < 8, data_1[cse_var_4 + threadIdx_x_1 // 3 * 7 + cse_var_3 + blockIdx_x % 7 + threadIdx_x_1 % 3 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 32):
- pad_temp_shared_1[threadIdx_x_1 + 32] = T.if_then_else(1 <= (threadIdx_x_1 + 11) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 + 11) % 21 // 3 + ry_outer_outer < 8 and 1 <= blockIdx_x % 7 + (threadIdx_x_1 + 2) % 3 and blockIdx_x % 7 + (threadIdx_x_1 + 2) % 3 < 8, data_1[cse_var_4 + (threadIdx_x_1 + 32) // 3 * 7 + cse_var_3 + blockIdx_x % 7 + (threadIdx_x_1 + 2) % 3 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 32):
- if T.likely(threadIdx_x_1 < 20):
- pad_temp_shared_1[threadIdx_x_1 + 64] = T.if_then_else(1 <= (threadIdx_x_1 + 1) // 3 + ry_outer_outer and (threadIdx_x_1 + 1) // 3 + ry_outer_outer < 8 and 1 <= blockIdx_x % 7 + (threadIdx_x_1 + 1) % 3 and blockIdx_x % 7 + (threadIdx_x_1 + 1) % 3 < 8, data_1[cse_var_4 + (threadIdx_x_1 + 64) // 3 * 7 + cse_var_3 + blockIdx_x % 7 + (threadIdx_x_1 + 1) % 3 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 49] = T.if_then_else(9 <= (threadIdx_x_1 + 49) % 81 and (threadIdx_x_1 + 49) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 49) // 81 * 49 + (threadIdx_x_1 + 49) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 98) // 81 * 49 + (threadIdx_x_1 + 17) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 147] = T.if_then_else(9 <= (threadIdx_x_1 + 66) % 81 and (threadIdx_x_1 + 66) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 147) // 81 * 49 + (threadIdx_x_1 + 66) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(9 <= (threadIdx_x_1 + 34) % 81 and (threadIdx_x_1 + 34) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 196) // 81 * 49 + (threadIdx_x_1 + 34) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 245] = T.if_then_else(7 <= threadIdx_x_1 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 245) // 81 * 49 + (threadIdx_x_1 + 2) // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(9 <= (threadIdx_x_1 + 51) % 81 and (threadIdx_x_1 + 51) % 81 < 72 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 294) // 81 * 49 + (threadIdx_x_1 + 51) % 81 // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 343] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 343) // 81 * 49 + (threadIdx_x_1 + 19) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(9 <= (threadIdx_x_1 + 68) % 81 and (threadIdx_x_1 + 68) % 81 < 72 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 392) // 81 * 49 + (threadIdx_x_1 + 68) % 81 // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 441] = T.if_then_else(1 <= (threadIdx_x_1 // 9 + 4) % 9 and (threadIdx_x_1 + 36) % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 441) // 81 * 49 + (threadIdx_x_1 // 9 + 4) % 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(5 <= threadIdx_x_1 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 490) // 81 * 49 + (threadIdx_x_1 + 4) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 539] = T.if_then_else(9 <= (threadIdx_x_1 + 53) % 81 and (threadIdx_x_1 + 53) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 539) // 81 * 49 + (threadIdx_x_1 + 53) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 588) // 81 * 49 + (threadIdx_x_1 + 21) // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 637] = T.if_then_else(9 <= (threadIdx_x_1 + 70) % 81 and (threadIdx_x_1 + 70) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 637) // 81 * 49 + (threadIdx_x_1 + 70) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(9 <= (threadIdx_x_1 + 38) % 81 and (threadIdx_x_1 + 38) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 686) // 81 * 49 + (threadIdx_x_1 + 38) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 735] = T.if_then_else(3 <= threadIdx_x_1 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 735) // 81 * 49 + (threadIdx_x_1 + 6) // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(9 <= (threadIdx_x_1 + 55) % 81 and (threadIdx_x_1 + 55) % 81 < 72 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 81 * 49 + (threadIdx_x_1 + 55) % 81 // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 833] = T.if_then_else(1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 833) // 81 * 49 + (threadIdx_x_1 + 23) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 882] = T.if_then_else(1 <= (threadIdx_x_1 // 9 + 8) % 9 and (threadIdx_x_1 + 72) % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 882) // 81 * 49 + (threadIdx_x_1 // 9 + 8) % 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 931] = T.if_then_else(9 <= (threadIdx_x_1 + 40) % 81 and (threadIdx_x_1 + 40) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 931) // 81 * 49 + (threadIdx_x_1 + 40) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 980] = T.if_then_else(1 <= threadIdx_x_1 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 980) // 81 * 49 + (threadIdx_x_1 + 8) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1029] = T.if_then_else(9 <= (threadIdx_x_1 + 57) % 81 and (threadIdx_x_1 + 57) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1029) // 81 * 49 + (threadIdx_x_1 + 57) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1078] = T.if_then_else(threadIdx_x_1 < 47 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1078) // 81 * 49 + (threadIdx_x_1 + 25) // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1127] = T.if_then_else(9 <= (threadIdx_x_1 + 74) % 81 and (threadIdx_x_1 + 74) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1127) // 81 * 49 + (threadIdx_x_1 + 74) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1176] = T.if_then_else(9 <= (threadIdx_x_1 + 42) % 81 and (threadIdx_x_1 + 42) % 81 < 72 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1176) // 81 * 49 + (threadIdx_x_1 + 42) % 81 // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ pad_temp_shared_1[threadIdx_x_1 + 1225] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1225) // 81 * 49 + (threadIdx_x_1 + 10) // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 49):
+ if T.likely(threadIdx_x_1 < 22):
+ pad_temp_shared_1[threadIdx_x_1 + 1274] = T.if_then_else(threadIdx_x_1 < 13 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1274) // 81 * 49 + (threadIdx_x_1 + 59) // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((768,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((2304,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 32) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 32) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 64) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 64) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 96] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 36864]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 128) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 128) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 160) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 160) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 192] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 73728]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 224) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 224) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 256) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 256) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 288] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 110592]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 320) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 320) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 352) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 352) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 384] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 147456]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 416) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 416) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 448) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 448) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 480] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 184320]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 512) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 512) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 544) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 544) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 576] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 221184]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 608) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 608) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 640) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 640) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_2 + threadIdx_x_2 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 258048]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 704) // 12 * 12 + (threadIdx_x_2 + 8) % 12 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 704) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 32):
- kernel_shared_1[(threadIdx_x_2 + 736) // 12 * 12 + (threadIdx_x_2 + 4) % 12 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 + 736) // 12 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- for rc_outer_inner, yy_outer_inner in T.grid(2, 7):
- cse_var_11: T.int32 = yy_outer_inner + 7
- cse_var_10: T.int32 = rc_outer_inner * 42 + yy_outer_inner * 3
- cse_var_9: T.int32 = cse_var_10 + 23
- cse_var_8: T.int32 = cse_var_10 + 22
- cse_var_7: T.int32 = cse_var_10 + 21
- cse_var_6: T.int32 = cse_var_10 + 2
- cse_var_5: T.int32 = cse_var_10 + 1
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_10] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_10] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 384]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_5] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 1]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_5] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 385]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_6] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 2]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_6] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 386]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_7] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 3]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_7] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 387]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_8] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 4]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_8] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 388]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[cse_var_9] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 5]
- conv2d_nchw_1[cse_var_11] = conv2d_nchw_1[cse_var_11] + pad_temp_shared_1[cse_var_9] * kernel_shared_1[threadIdx_x * 12 + rc_outer_inner * 6 + 389]
- for i2_inner in range(7):
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 49] = kernel_1[blockIdx_x * 73728 + cse_var_1 + threadIdx_x_2 + 49]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 98) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 147] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 147) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 3]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 52]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 245] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 245) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 101) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 294] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 294) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 6]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 343] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 343) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 55]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 392] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 392) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 104) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 441] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 441) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 9]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 490] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 490) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 58]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 539] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 539) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 107) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 588] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 588) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 12]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 637] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 637) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 61]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 686] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 686) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 110) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 735] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 735) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 15]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 784) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 64]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 833] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 833) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 113) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 882] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 882) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 18]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 931] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 931) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 67]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 980] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 980) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 116) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1029] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1029) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 21]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1078] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1078) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 70]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1127] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1127) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 119) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1176] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1176) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 24]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1225] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1225) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 73]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1274] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1274) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 122) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1323] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1323) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 27]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1372] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1372) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 76]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1421] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1421) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 125) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1470] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1470) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 30]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1519] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1519) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 79]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1568) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1617] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1617) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 33]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1666] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1666) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 82]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1715] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1715) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 131) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1764] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1764) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 36]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1813] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1813) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 85]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1862] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1862) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 134) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1911] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1911) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 39]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 1960] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1960) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 88]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2009] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2009) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 137) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2058] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2058) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 42]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2107] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2107) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 91]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2156] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2156) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 140) % 144]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2205] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2205) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 45]
+ with T.launch_thread(threadIdx_x_2, 49):
+ kernel_shared_1[threadIdx_x_2 + 2254] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2254) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 94]
+ with T.launch_thread(threadIdx_x_2, 49):
+ if T.likely(threadIdx_x_2 < 1):
+ kernel_shared_1[threadIdx_x_2 + 2303] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2303) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 143]
+ for rc_inner in range(16):
+ cse_var_3: T.int32 = rc_inner * 9
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 288]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 576]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 864]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1152]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1440]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1728]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 2016]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 144]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 432]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 720]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1008]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1296]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1584]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 1872]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7] * kernel_shared_1[cse_var_3 + 2160]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 289]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 577]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 865]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1153]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1441]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1729]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 2017]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 145]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 433]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 721]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1009]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1297]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1585]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 1873]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[cse_var_3 + 2161]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 290]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 578]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 866]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1154]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1442]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1730]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 2018]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 146]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 434]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 722]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1010]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1298]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1586]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 1874]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[cse_var_3 + 2162]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 291]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 579]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 867]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1155]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1443]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1731]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 2019]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 147]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 435]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 723]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1011]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1299]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1587]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 1875]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 9] * kernel_shared_1[cse_var_3 + 2163]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 292]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 580]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 868]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1156]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1444]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1732]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 2020]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 148]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 436]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 724]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1012]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1300]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1588]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 1876]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 10] * kernel_shared_1[cse_var_3 + 2164]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 293]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 581]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 869]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1157]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1445]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1733]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 2021]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 149]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 437]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 725]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1013]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1301]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1589]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 1877]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 11] * kernel_shared_1[cse_var_3 + 2165]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 294]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 582]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 870]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1158]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1446]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1734]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 2022]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 150]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 438]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 726]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1014]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1302]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1590]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 1878]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 18] * kernel_shared_1[cse_var_3 + 2166]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 295]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 583]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 871]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1159]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1447]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1735]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 2023]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 151]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 439]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 727]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1015]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1303]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1591]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 1879]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 19] * kernel_shared_1[cse_var_3 + 2167]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 296]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 584]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 872]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1160]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1448]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1736]
+ conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 2024]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 152]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 440]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 728]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1016]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1304]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1592]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 1880]
+ conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x // 7 * 9 + threadIdx_x % 7 + 20] * kernel_shared_1[cse_var_3 + 2168]
+ for i1_inner in range(2):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x // 7 * 3136 + threadIdx_x * 49 + i2_inner * 7 + blockIdx_x % 7] = T.max(conv2d_nchw_1[i2_inner] + bias_1[blockIdx_x // 7 * 64 + threadIdx_x], T.float32(0))
- compute_1[blockIdx_x // 7 * 3136 + threadIdx_x * 49 + i2_inner * 7 + blockIdx_x % 7 + 1568] = T.max(conv2d_nchw_1[i2_inner + 7] + bias_1[blockIdx_x // 7 * 64 + threadIdx_x + 32], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 98] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 16 + i1_inner + 2], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 196] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 16 + i1_inner + 4], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 294] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_1[blockIdx_x * 16 + i1_inner + 6], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 392] = T.max(conv2d_nchw_1[i1_inner + 8] + bias_1[blockIdx_x * 16 + i1_inner + 8], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 490] = T.max(conv2d_nchw_1[i1_inner + 10] + bias_1[blockIdx_x * 16 + i1_inner + 10], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 588] = T.max(conv2d_nchw_1[i1_inner + 12] + bias_1[blockIdx_x * 16 + i1_inner + 12], T.float32(0))
+ compute_1[blockIdx_x * 784 + i1_inner * 49 + threadIdx_x + 686] = T.max(conv2d_nchw_1[i1_inner + 14] + bias_1[blockIdx_x * 16 + i1_inner + 14], T.float32(0))
</pre></div>
</div>
</div>
@@ -654,7 +883,7 @@ class Module:
<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: 0.422 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.273 ms
</pre></div>
</div>
</div>
@@ -683,21 +912,21 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
-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=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=8)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=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_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
@@ -705,14 +934,14 @@ s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, 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=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=8)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -732,14 +961,14 @@ 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=32)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 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:
@@ -757,78 +986,264 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[84];
- __shared__ float kernel_shared[768];
+extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[16];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[2304];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.0000 [...]
- pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((1 <= ((((((int)threadIdx.x) + 11) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 11) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 32) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + [...]
- if (((int)threadIdx.x) < 20) {
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= (((((int)threadIdx.x) + 1) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) + 1) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 64) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)thread [...]
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 32) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 32) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 64) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((((((int)threadIdx.x) + 128) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 160) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 160) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((((((int)threadIdx.x) + 224) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 224) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 256) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((((((int)threadIdx.x) + 320) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 352) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 352) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((((((int)threadIdx.x) + 416) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 416) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 448) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((((((int)threadIdx.x) + 512) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 544) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 544) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((((((int)threadIdx.x) + 608) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 608) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 640) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((((((int)threadIdx.x) + 704) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 736) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 736) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((rc_outer_inner * 42) + (yy_outer_inner * 3))] * kernel_shared[((((int)threadIdx.x) * 12) + (rc_outer_inner * 6))]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[((rc_outer_inner * 42) + (yy_outer_inner * 3))] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 384)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 1)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 1)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 385)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 2)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 2)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 386)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 21)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 21)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 387)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 22)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 22)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 388)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 23)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[(yy_outer_inner + 7)] = (conv2d_nchw[(yy_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 42) + (yy_outer_inner * 3)) + 23)] * kernel_shared[(((((int)threadIdx.x) * 12) + (rc_outer_inner * 6)) + 389)]));
- }
- }
+ conv2d_nchw[15] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = (((((9 <= ((((int)threadIdx.x) + 70) % 81)) && (((((int)threadIdx.x) + 70) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 637) / 81) * 49)) + ((((((int)threadIdx.x) + 70) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 735)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 735) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 833)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 833) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((9 <= ((((int)threadIdx.x) + 40) % 81)) && (((((int)threadIdx.x) + 40) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 931) / 81) * 49)) + ((((((int)threadIdx.x) + 40) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 980) / 81) * 49)) + (((((int)threadIdx.x) + 8) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((9 <= ((((int)threadIdx.x) + 57) % 81)) && (((((int)threadIdx.x) + 57) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1029) / 81) * 49)) + ((((((int)threadIdx.x) + 57) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + (((((int)threadIdx.x) + 25) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1127) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1225) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 22) {
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + (((((int)threadIdx.x) + 59) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 49)];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 98) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 147) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 3)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 52)];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 245) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 101) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 343) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 55)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 104) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 441)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 441) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9)];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 58)];
+ kernel_shared[(((int)threadIdx.x) + 539)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 539) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 107) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 637)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 637) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 61)];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 110) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 735)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 735) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 15)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64)];
+ kernel_shared[(((int)threadIdx.x) + 833)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 833) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 113) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 18)];
+ kernel_shared[(((int)threadIdx.x) + 931)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 931) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 67)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 116) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1029) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 21)];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 70)];
+ kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1127) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 119) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1225)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1225) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 73)];
+ kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 122) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1323)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1323) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 27)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 76)];
+ kernel_shared[(((int)threadIdx.x) + 1421)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1421) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 125) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 30)];
+ kernel_shared[(((int)threadIdx.x) + 1519)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1519) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 79)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1617)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1617) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 33)];
+ kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 82)];
+ kernel_shared[(((int)threadIdx.x) + 1715)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1715) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 131) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 1813)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1813) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 85)];
+ kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 134) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 1911)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1911) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 39)];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 88)];
+ kernel_shared[(((int)threadIdx.x) + 2009)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2009) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 137) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 42)];
+ kernel_shared[(((int)threadIdx.x) + 2107)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2107) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 91)];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 140) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 2205)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2205) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 45)];
+ kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 94)];
+ if (((int)threadIdx.x) < 1) {
+ kernel_shared[(((int)threadIdx.x) + 2303)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2303) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 143)];
+ }
+ __syncthreads();
+ for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_inner * 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 288)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 576)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 864)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1152)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1440)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1728)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 2016)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 432)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 720)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1008)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1296)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1584)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 1872)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 2160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 289)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 577)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 865)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1153)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1441)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1729)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 2017)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 145)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 433)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 721)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1009)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1297)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1585)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1873)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 2161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 290)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 578)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 866)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1154)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1442)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1730)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 2018)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 146)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 434)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 722)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1010)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1298)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1586)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 1874)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 2162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 291)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 579)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 867)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1155)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1443)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1731)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 2019)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 147)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 435)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 723)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1011)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1299)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1587)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 1875)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 2163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 292)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 580)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 868)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1156)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1444)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1732)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 2020)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 148)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 436)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 724)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1012)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1300)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1588)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 1876)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 2164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 293)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 581)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 869)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1157)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1445)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1733)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 2021)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 149)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 437)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 725)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1013)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1301)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1589)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 1877)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 2165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 294)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 582)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 870)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1158)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1446)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1734)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 2022)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 150)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 438)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 726)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1014)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1302)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1590)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 1878)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 2166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 295)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 583)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 871)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1159)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1447)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1735)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 2023)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 151)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 439)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 727)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1015)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1303)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1591)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 1879)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 2167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 296)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 584)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 872)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1160)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1448)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1736)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 2024)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 152)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 440)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 728)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1016)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1304)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1592)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 1880)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 2168)]));
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7)) + 1568)] = max((conv2d_nchw[(i2_inner + 7)] + bias[((((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x)) + 32)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 2)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 294)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 6)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 490)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 10)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 12)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 686)] = max((conv2d_nchw[(i1_inner + 14)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 14)]), 0.000000e+00f);
}
}
</pre></div>
@@ -863,7 +1278,7 @@ 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> ( 6 minutes 14.710 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 14.017 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 6fb9b8a33b..d51bc28915 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.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)
- 8.0860 8.0890 8.0948 8.0743 0.0086
+ 8.1509 8.1473 8.1641 8.1413 0.0096
</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 10.615 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.970 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_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_network_cuda.py</span></code></a></p>
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 379ea813ea..f6f1fae625 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -940,7 +940,7 @@ 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)
- 759.8484 759.4011 760.9119 759.2323 0.7551
+ 767.9541 766.9722 770.3072 766.5829 1.6715
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ 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 42.353 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 46.369 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 71215ef7fb..b775160c43 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -637,74 +637,26 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(128):
- compute_1 = T.allocate([512], "float32", "global")
- compute_2 = T.Buffer((512,), data=compute_1)
+ for i0_outer_i1_outer_fused in T.parallel(64):
+ compute_1 = T.allocate([1024], "float32", "global")
+ compute_2 = T.Buffer((1024,), data=compute_1)
for nb_j_inner in range(2):
- for i_inner_init in range(16):
- cse_var_1: T.int32 = i_inner_init * 32 + nb_j_inner * 16
- compute_2[cse_var_1] = T.float32(0)
- compute_2[cse_var_1 + 1] = T.float32(0)
- compute_2[cse_var_1 + 2] = T.float32(0)
- compute_2[cse_var_1 + 3] = T.float32(0)
- compute_2[cse_var_1 + 4] = T.float32(0)
- compute_2[cse_var_1 + 5] = T.float32(0)
- compute_2[cse_var_1 + 6] = T.float32(0)
- compute_2[cse_var_1 + 7] = T.float32(0)
- compute_2[cse_var_1 + 8] = T.float32(0)
- compute_2[cse_var_1 + 9] = T.float32(0)
- compute_2[cse_var_1 + 10] = T.float32(0)
- compute_2[cse_var_1 + 11] = T.float32(0)
- compute_2[cse_var_1 + 12] = T.float32(0)
- compute_2[cse_var_1 + 13] = T.float32(0)
- compute_2[cse_var_1 + 14] = T.float32(0)
- compute_2[cse_var_1 + 15] = T.float32(0)
- for elem_idx, i_inner in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 16):
- cse_var_2 = T.int32()
+ for i_inner_init, j_init in T.grid(32, 16):
+ compute_2[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 32, 16):
+ cse_var_1 = T.int32()
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_21: T.int32 = elem_idx * 16
- cse_var_20: T.int32 = i_inner * 32 + nb_j_inner * 16
- cse_var_19: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_18: T.int32 = i0_outer_i1_outer_fused // 16 * 4096 + i_inner * 256
- cse_var_17: T.int32 = cse_var_20 + 9
- cse_var_16: T.int32 = cse_var_20 + 8
- cse_var_15: T.int32 = cse_var_20 + 7
- cse_var_14: T.int32 = cse_var_20 + 6
- cse_var_13: T.int32 = cse_var_20 + 5
- cse_var_12: T.int32 = cse_var_20 + 4
- cse_var_11: T.int32 = cse_var_20 + 3
- cse_var_10: T.int32 = cse_var_20 + 2
- cse_var_9: T.int32 = cse_var_20 + 15
- cse_var_8: T.int32 = cse_var_20 + 14
- cse_var_7: T.int32 = cse_var_20 + 13
- cse_var_6: T.int32 = cse_var_20 + 12
- cse_var_5: T.int32 = cse_var_20 + 11
- cse_var_4: T.int32 = cse_var_20 + 10
- cse_var_3: T.int32 = cse_var_20 + 1
+ cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
- for i0_inner in range(16):
- cse_var_22: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 8192 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner, i1_inner in T.grid(32, 32):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_22:cse_var_22 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_22:cse_var_22 + 32], T.Broadcast(T.float32(0), 32))
+ compute_3[cse_var_4] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_4], T.float32(0))
</pre></div>
</div>
</div>
@@ -738,7 +690,7 @@ class Module:
<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: 1.674 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.661 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 6f23fb95db..89fc29c25d 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:31.101</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.709</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:31.066</p></td>
+<td><p>00:44.671</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>00:00.024</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>
@@ -366,7 +366,7 @@
<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>
-<td><p>00:00.005</p></td>
+<td><p>00:00.004</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
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 a824212912..b814c9e1f8 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -695,8 +695,11 @@ 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 875, 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, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9685816
-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, 1, 8, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1656577
+No: 2 GFLOPS: 240.37/240.37 result: MeasureResult(costs=(0.000963099981981982,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8540472984313965, timestamp=1679480318.6655898) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4775456
+No: 3 GFLOPS: 11.68/240.37 result: MeasureResult(costs=(0.019824858333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7285661697387695, timestamp=1679480319.670046) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4700806
+No: 4 GFLOPS: 11.96/240.37 result: MeasureResult(costs=(0.019355658166666668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.30946683883667, timestamp=1679480322.1305206) [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9389098
+No: 5 GFLOPS: 0.00/240.37 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -818,8 +821,26 @@ 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 875, 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, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3065192
-No: 3 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, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7452442
+No: 6 GFLOPS: 0.00/240.37 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9617960
+No: 7 GFLOPS: 0.00/240.37 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -941,9 +962,8 @@ 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 875, 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, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9756393
-No: 4 GFLOPS: 63.61/63.61 result: MeasureResult(costs=(0.0036392384,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1150307655334473, timestamp=1679480272.8978193) [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,399155
-No: 5 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+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, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1667464
+No: 8 GFLOPS: 0.00/240.37 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1065,8 +1085,9 @@ 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 875, 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, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4364226
-No: 6 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4411577
+No: 9 GFLOPS: 263.35/263.35 result: MeasureResult(costs=(0.0008790775027932962,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9729106426239014, timestamp=1679480336.942195) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4752474
+No: 10 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1188,8 +1209,8 @@ 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 875, 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, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,905819
-No: 7 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4764912
+No: 11 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1311,8 +1332,8 @@ 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 875, 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, 4, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3502828
-No: 8 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7511271
+No: 12 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1434,8 +1455,8 @@ 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 875, 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, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4407883
-No: 9 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6211255
+No: 13 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1557,8 +1578,8 @@ 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 875, 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, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1191008
-No: 10 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9672716
+No: 14 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1680,8 +1701,8 @@ 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 875, 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, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8381635
-No: 11 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,636386
+No: 15 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1803,8 +1824,8 @@ 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 875, 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, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1961907
-No: 12 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7583033
+No: 16 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1926,8 +1947,8 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10111342
-No: 13 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5254791
+No: 17 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2049,8 +2070,8 @@ 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 875, 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, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3321167
-No: 14 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5979400
+No: 18 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2172,8 +2193,8 @@ 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 875, 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, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5013278
-No: 15 GFLOPS: 0.00/63.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9805266
+No: 19 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2295,10 +2316,8 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10014083
-No: 16 GFLOPS: 283.04/283.04 result: MeasureResult(costs=(0.0008179004712643678,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6042275428771973, timestamp=1679480278.1020658) [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2522137
-No: 17 GFLOPS: 199.37/283.04 result: MeasureResult(costs=(0.0011611694772727273,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9948115348815918, timestamp=1679480281.3582416) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1620973
-No: 18 GFLOPS: 0.00/283.04 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9955226
+No: 20 GFLOPS: 0.00/263.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2420,9 +2439,7 @@ 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 875, 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, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5978366
-No: 19 GFLOPS: 156.35/283.04 result: MeasureResult(costs=(0.0014806446666666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5363528728485107, timestamp=1679480282.2197342) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2203963
-No: 20 GFLOPS: 92.07/283.04 result: MeasureResult(costs=(0.00251453685,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9266879558563232, timestamp=1679480283.0750692) [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8008761
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4778051
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2461,9 +2478,9 @@ 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, 4, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2522137
+[('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4752474
Finish loading 20 records
-Time cost of this operator: 0.001276
+Time cost of this operator: 0.001240
</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 baebaa42b4..7b324046a6 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -649,10 +649,10 @@ 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 315.1 98.743 (1, 2, 10, 10, 3) 2 1 [315.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.953 (1, 6, 10, 10) 1 1 [3.042]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.304 (1, 1, 10, 10, 3) 1 1 [0.97]
-Total_time - 319.112 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.6 98.741 (1, 2, 10, 10, 3) 2 1 [316.6]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.07 0.958 (1, 6, 10, 10) 1 1 [3.07]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.302 (1, 1, 10, 10, 3) 1 1 [0.968]
+Total_time - 320.638 - - - - -
</pre></div>
</div>
</div>
@@ -704,13 +704,13 @@ 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 103.0 97.5 (1, 6, 10, 10, 1) 2 1 [103.0]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.785 1.69 (1, 6, 10, 10) 1 1 [1.785]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.856 0.81 (1, 3, 10, 10, 1) 1 1 [0.856]
-Total_time - 105.641 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 101.7 97.356 (1, 6, 10, 10, 1) 2 1 [101.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.795 1.718 (1, 6, 10, 10) 1 1 [1.795]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 0.926 (1, 1, 10, 10, 3) 1 1 [0.967]
+Total_time - 104.462 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.041 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.178 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_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 421bc276fd..0deb97d650 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -460,7 +460,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 106MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 166MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -586,7 +586,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.927 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.497 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_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">micro_pytorch.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 e860f402f5..c7a11c72ee 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -528,7 +528,7 @@ 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/tmp7kq46wp_/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpuksbrz7v/images/random'
</pre></div>
</div>
</div>
@@ -588,8 +588,8 @@ 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="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp7kq46wp_/images/target contains 8144 images
-/tmp/tmp7kq46wp_/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], [1.0, 0.0], [0.0, 1.0], [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]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpuksbrz7v/images/target contains 8144 images
+/tmp/tmpuksbrz7v/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -701,13 +701,13 @@ 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 - 41s - loss: 0.2246 - accuracy: 0.9236 - val_loss: 0.1052 - val_accuracy: 0.9649 - 41s/epoch - 124ms/step
+328/328 - 41s - loss: 0.2223 - accuracy: 0.9224 - val_loss: 0.1851 - val_accuracy: 0.9392 - 41s/epoch - 125ms/step
Epoch 2/3
-328/328 - 35s - loss: 0.1028 - accuracy: 0.9637 - val_loss: 0.1085 - val_accuracy: 0.9664 - 35s/epoch - 106ms/step
+328/328 - 35s - loss: 0.1118 - accuracy: 0.9596 - val_loss: 0.1019 - val_accuracy: 0.9626 - 35s/epoch - 107ms/step
Epoch 3/3
-328/328 - 35s - loss: 0.0732 - accuracy: 0.9721 - val_loss: 0.1114 - val_accuracy: 0.9664 - 35s/epoch - 105ms/step
+328/328 - 35s - loss: 0.0660 - accuracy: 0.9739 - val_loss: 0.1076 - val_accuracy: 0.9649 - 35s/epoch - 106ms/step
-<keras.callbacks.History object at 0x7f84a5364710>
+<keras.callbacks.History object at 0x7fd37936ba10>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ 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> ( 3 minutes 49.126 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 48.717 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 24b70ac3af..fb546c3bbc 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>06:52.937</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:57.874</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,27 +354,27 @@
</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">5. 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>03:49.126</p></td>
+<td><p>03:48.717</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">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:21.041</p></td>
+<td><p>01:26.178</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:16.927</p></td>
+<td><p>01:16.497</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:10.301</p></td>
+<td><p>00:10.155</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_custom_ide.html#sphx-glr-how-to-work-with-microtvm-micro-custom-ide-py"><span class="std std-ref">9. Bring microTVM to your own development environment</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_custom_ide.py</span></code>)</p></td>
-<td><p>00:07.980</p></td>
+<td><p>00:08.512</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">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.561</p></td>
+<td><p>00:07.816</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">7. 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 2cd8777ae6..d3ef8bfda7 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:36.262</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:37.060</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.806</p></td>
+<td><p>00:32.337</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>00:02.856</p></td>
+<td><p>00:02.876</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>00:01.593</p></td>
+<td><p>00:01.840</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 96bf8aad57..8a66a2cbb5 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -540,7 +540,7 @@ 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 0x7f80efe03830>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fd11222b5f0>
</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 a31132e544..4a1d410bfc 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:07.048</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.884</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</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>00:04.132</p></td>
+<td><p>00:02.959</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.406</p></td>
+<td><p>00:01.438</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>00:00.622</p></td>
+<td><p>00:00.613</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>00:00.611</p></td>
+<td><p>00:00.600</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>00:00.129</p></td>
+<td><p>00:00.128</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.063</p></td>
+<td><p>00:00.062</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.055</p></td>
+<td><p>00:00.054</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.029</p></td>
+<td><p>00:00.030</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 1515c4b747..e285b427a5 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -234,7 +234,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/objects.inv b/docs/objects.inv
index e90f22abc4..b00712a008 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode-members.html b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode-members.html
index 62fe7d7f43..ca2f13289a 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode-members.html
@@ -166,10 +166,11 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a7c310bca5d1583e61a3f27052a1dd5d0">Unannotate</a>(const BlockRV &block_rv, const String &ann_key)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7">unique</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_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552">Unroll</a>(const LoopRV &loop_rv)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ab4a8cd91959ceab22855ec338978bcee">Vectorize</a>(const LoopRV &loop_rv)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#acb747d074e1f99477f7132e4614221a3">WorkOn</a>(const String &func_name)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ad66f22b795a1e34cb3c42e691e5864a7">WriteAt</a>(const LoopRV &loop_rv, const BlockRV &block_rv, int write_buffer_index, const String &storage_scope)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ae637f126412479ed9bec05fd55376f7f">~ScheduleNode</a>()=default</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ac797a00135c910d65da297038b930ed6">UnsafeSetDType</a>(const BlockRV &block_rv, int buffer_index, const String &dtype)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ab4a8cd91959ceab22855ec338978bcee">Vectorize</a>(const LoopRV &loop_rv)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#acb747d074e1f99477f7132e4614221a3">WorkOn</a>(const String &func_name)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ad66f22b795a1e34cb3c42e691e5864a7">WriteAt</a>(const LoopRV &loop_rv, const BlockRV &block_rv, int write_buffer_index, const String &storage_scope)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ae637f126412479ed9bec05fd55376f7f">~ScheduleNode</a>()=default</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
</table></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode.html b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode.html
index ccaeb2eda6..6c0f0a6689 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode.html
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode.html
@@ -248,8 +248,11 @@ Public Member Functions</h2></td></tr>
<tr class="memdesc:a93d1d23f24d903db844f75f51fe09a36"><td class="mdescLeft"> </td><td class="mdescRight">Set alignment requirement for specific dimension such that stride[axis] == k * factor + offset for some k. This is useful to set memory layout for more friendly memory access pattern. <a class="el" href="classtvm_1_1tir_1_1For.html" title="Managed reference to ForNode. ">For</a> example, we can set alignment to be factor=2, offset=1 to avoid bank conflict for thread access on hig [...]
<tr class="separator:a93d1d23f24d903db844f75f51fe09a36"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:aa4760135d373af488a08aaeba7114c48"><td class="memItemLeft" align="right" valign="top">virtual void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#aa4760135d373af488a08aaeba7114c48">SetScope</a> (const <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> &block_rv, int buffer_index, const <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> &storage_scope)=0</td></tr>
-<tr class="memdesc:aa4760135d373af488a08aaeba7114c48"><td class="mdescLeft"> </td><td class="mdescRight">Set the storage scope of a buffer, where the buffer is specified by the a block and a write-index. <a href="#aa4760135d373af488a08aaeba7114c48">More...</a><br /></td></tr>
+<tr class="memdesc:aa4760135d373af488a08aaeba7114c48"><td class="mdescLeft"> </td><td class="mdescRight">Set the storage scope of a buffer, where the buffer is specified by a block and a write-index. <a href="#aa4760135d373af488a08aaeba7114c48">More...</a><br /></td></tr>
<tr class="separator:aa4760135d373af488a08aaeba7114c48"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ac797a00135c910d65da297038b930ed6"><td class="memItemLeft" align="right" valign="top">virtual void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ac797a00135c910d65da297038b930ed6">UnsafeSetDType</a> (const <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> &block_rv, int buffer_index, const <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> &dtype)=0</td></tr>
+<tr class="memdesc:ac797a00135c910d65da297038b930ed6"><td class="mdescLeft"> </td><td class="mdescRight">Set the data type of a buffer, where the buffer is specified by a block and a write-index. <a href="#ac797a00135c910d65da297038b930ed6">More...</a><br /></td></tr>
+<tr class="separator:ac797a00135c910d65da297038b930ed6"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:ad519f290c705afd441eaf683c4e24693"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ad519f290c705afd441eaf683c4e24693">Blockize</a> (const <a class="el" href="classtvm_1_1tir_1_1LoopRV.html">LoopRV</a> &loop_rv, bool preserve_unit_iters=true)=0</td></tr>
<tr class="memdesc:ad519f290c705afd441eaf683c4e24693"><td class="mdescLeft"> </td><td class="mdescRight">Convert the subtree rooted at a specific loop into a block. <a href="#ad519f290c705afd441eaf683c4e24693">More...</a><br /></td></tr>
<tr class="separator:ad519f290c705afd441eaf683c4e24693"><td class="memSeparator" colspan="2"> </td></tr>
@@ -2680,7 +2683,7 @@ Additional Inherited Members</h2></td></tr>
</table>
</div><div class="memdoc">
-<p>Set the storage scope of a buffer, where the buffer is specified by the a block and a write-index. </p>
+<p>Set the storage scope of a buffer, where the buffer is specified by a block and a write-index. </p>
<dl class="params"><dt>Parameters</dt><dd>
<table class="params">
<tr><td class="paramname">block_rv</td><td>The producer block of the buffer </td></tr>
@@ -3241,6 +3244,59 @@ Additional Inherited Members</h2></td></tr>
</dd>
</dl>
+</div>
+</div>
+<a id="ac797a00135c910d65da297038b930ed6"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#ac797a00135c910d65da297038b930ed6">◆ </a></span>UnsafeSetDType()</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">virtual void tvm::tir::ScheduleNode::UnsafeSetDType </td>
+ <td>(</td>
+ <td class="paramtype">const <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> & </td>
+ <td class="paramname"><em>block_rv</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">int </td>
+ <td class="paramname"><em>buffer_index</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">const <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> & </td>
+ <td class="paramname"><em>dtype</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">pure virtual</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>Set the data type of a buffer, where the buffer is specified by a block and a write-index. </p>
+<dl class="section note"><dt>Note</dt><dd>This schedule primitive is unsafe and may change correctness of program because of type conversion, please use with caution. </dd></dl>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">block_rv</td><td>The producer block of the buffer </td></tr>
+ <tr><td class="paramname">buffer_index</td><td>the index of the buffer in block's write region </td></tr>
+ <tr><td class="paramname">dtype</td><td>The data type to be set </td></tr>
+ </table>
+ </dd>
+</dl>
+
</div>
</div>
<a id="ab4a8cd91959ceab22855ec338978bcee"></a>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode__coll__graph.svg
index ac83a66c4f..65f01b63b8 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode__coll__graph.svg
@@ -27,7 +27,7 @@
<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Seed()</text>
<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ForkSeed()</text>
<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Get()</text>
-<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 59 more...</text>
+<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 60 more...</text>
</g>
<!-- Node3 -->
<g id="node2" class="node">
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode__inherit__graph.svg
index bb94788d47..acf3326b6a 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode__inherit__graph.svg
@@ -27,7 +27,7 @@
<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Seed()</text>
<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ForkSeed()</text>
<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Get()</text>
-<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 59 more...</text>
+<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 60 more...</text>
</g>
<!-- Node1 -->
<g id="node2" class="node">
diff --git a/docs/reference/api/doxygen/database_8h_source.html b/docs/reference/api/doxygen/database_8h_source.html
index b48f767bfe..713f3e0a62 100644
--- a/docs/reference/api/doxygen/database_8h_source.html
+++ b/docs/reference/api/doxygen/database_8h_source.html
@@ -85,7 +85,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1meta__schedule_1_1WorkloadHash_html_a7cb09ddc6c76d9d00ddbeab8502d97cb"><div class="ttname"><a href="structtvm_1_1meta__schedule_1_1WorkloadHash.html#a7cb09ddc6c76d9d00ddbeab8502d97cb">tvm::meta_schedule::WorkloadHash::operator()</a></div><div class="ttdeci">size_t operator()(const Workload &a) const</div><div class="ttdef"><b>Definition:</b> database.h:96</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html">tvm::meta_schedule::PyDatabaseNode</a></div><div class="ttdoc">The database with customized methods on the python-side. </div><div class="ttdef"><b>Definition:</b> database.h:277</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:778</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:788</div></div>
<div class="ttc" id="structtvm_1_1meta__schedule_1_1WorkloadEqual_html_a49b0e137a01a278469ff63729afae804"><div class="ttname"><a href="structtvm_1_1meta__schedule_1_1WorkloadEqual.html#a49b0e137a01a278469ff63729afae804">tvm::meta_schedule::WorkloadEqual::WorkloadEqual</a></div><div class="ttdeci">WorkloadEqual(const ModuleEquality &mod_eq)</div><div class="ttdef"><b>Definition:</b> database.h:101</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TuningRecordNode_html_a8cc2d64f796593a1a774eef259f17b29"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29">tvm::meta_schedule::TuningRecordNode::trace</a></div><div class="ttdeci">tir::Trace trace</div><div class="ttdoc">The trace tuned. </div><div class="ttdef"><b>Definition:</b> database.h:117</div></div>
<div class="ttc" id="arg__info_8h_html"><div class="ttname"><a href="arg__info_8h.html">arg_info.h</a></div></div>
diff --git a/docs/reference/api/doxygen/functions_func_u.html b/docs/reference/api/doxygen/functions_func_u.html
index 4b4e0f203d..217d340053 100644
--- a/docs/reference/api/doxygen/functions_func_u.html
+++ b/docs/reference/api/doxygen/functions_func_u.html
@@ -97,6 +97,9 @@ $(function() {
<li>Unroll()
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552">tvm::tir::ScheduleNode</a>
</li>
+<li>UnsafeSetDType()
+: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ac797a00135c910d65da297038b930ed6">tvm::tir::ScheduleNode</a>
+</li>
<li>Update()
: <a class="el" href="classtvm_1_1arith_1_1CanonicalSimplifier.html#a790c032e12c7d93e9e940297b860c509">tvm::arith::CanonicalSimplifier</a>
, <a class="el" href="classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7">tvm::arith::ConstIntBoundAnalyzer</a>
@@ -106,7 +109,7 @@ $(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#a94a93385e64ce844299729af6a573015">tvm::IRModuleNode</a>
+, <a class="el" href="classtvm_1_1IRModuleNode.html#abdd8936c6fca33ef9b7c086f8fd58f84">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_p.html b/docs/reference/api/doxygen/functions_p.html
index 799512a93e..88ac5927b0 100644
--- a/docs/reference/api/doxygen/functions_p.html
+++ b/docs/reference/api/doxygen/functions_p.html
@@ -419,7 +419,7 @@ $(function() {
, <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a39e0b263ee316310a3fcd85d3532763b">tvm::meta_schedule::SearchStrategyNode</a>
</li>
<li>PrimExpr()
-: <a class="el" href="classtvm_1_1PrimExpr.html#a756d3f8b17b019560946524951ae6118">tvm::PrimExpr</a>
+: <a class="el" href="classtvm_1_1PrimExpr.html#a7f0ca30e951608a0b36a77a66d4d19e0">tvm::PrimExpr</a>
</li>
<li>PrimFunc()
: <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html#ae45eed6cc7af5f9806be4709e87d1420">tvm::tir::PrimFunc</a>
diff --git a/docs/reference/api/doxygen/functions_s.html b/docs/reference/api/doxygen/functions_s.html
index 3d21708a71..657c134382 100644
--- a/docs/reference/api/doxygen/functions_s.html
+++ b/docs/reference/api/doxygen/functions_s.html
@@ -1089,7 +1089,7 @@ $(function() {
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a93d1d23f24d903db844f75f51fe09a36">tvm::tir::ScheduleNode</a>
</li>
<li>StorageAlignStep()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1StorageAlignStep.html#af50b7c2f020f8e0a80f5bcc8e559b394">tvm::auto_scheduler::StorageAlignStep</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1StorageAlignStep.html#a99dbb8c55d9e7d78268b6d43fd348bc7">tvm::auto_scheduler::StorageAlignStep</a>
</li>
<li>StorageType
: <a class="el" href="classtvm_1_1runtime_1_1SimpleObjAllocator_1_1ArrayHandler.html#a67e86db3290b1d3bd4aca7e7a2faf187">tvm::runtime::SimpleObjAllocator::ArrayHandler< ArrayType, ElemType ></a>
@@ -1150,7 +1150,7 @@ $(function() {
, <a class="el" href="classtvm_1_1tir_1_1BufferNode.html#ac18ddd10b79a30ae57d3a8283686259d">tvm::tir::BufferNode</a>
</li>
<li>String()
-: <a class="el" href="classtvm_1_1runtime_1_1String.html#a02fca36e3ff55cc1e83635b02a11fca3">tvm::runtime::String</a>
+: <a class="el" href="classtvm_1_1runtime_1_1String.html#ac5d930b522e9fef9c07e51819d96d2f3">tvm::runtime::String</a>
, <a class="el" href="classtvm_1_1runtime_1_1StringObj_1_1FromStd.html#a7fb804f7dc96dd9f705c84095f37f1ca">tvm::runtime::StringObj::FromStd</a>
, <a class="el" href="classtvm_1_1runtime_1_1StringObj.html#a7fb804f7dc96dd9f705c84095f37f1ca">tvm::runtime::StringObj</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_t.html b/docs/reference/api/doxygen/functions_t.html
index c158dd7556..a48e05427c 100644
--- a/docs/reference/api/doxygen/functions_t.html
+++ b/docs/reference/api/doxygen/functions_t.html
@@ -202,7 +202,7 @@ $(function() {
: <a class="el" href="classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d">tvm::te::Stage</a>
</li>
<li>Tensorize()
-: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#afa67abdb51145a49d42cd1464429d928">tvm::tir::ScheduleNode</a>
+: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a66983e2dde6aeb18b443616398fff8bf">tvm::tir::ScheduleNode</a>
</li>
<li>TensorNode()
: <a class="el" href="classtvm_1_1te_1_1TensorNode.html#a153569448cb1bf9d2924d35639c3b8b8">tvm::te::TensorNode</a>
@@ -1515,7 +1515,7 @@ $(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#afd8ee9dd9648c19b468bb4b0b00e8e4e">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#aa3663a440db7a6951abd767109b9bf90">tvm::runtime::TypedPackedFunc< R(Args...)></a>
</li>
<li>TypeIndex2Key()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
@@ -1538,7 +1538,7 @@ $(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>types
: <a class="el" href="classtvm_1_1TupleAffineTypeNode.html#a30c834b7e1cb64467e6587ac16ebb187">tvm::TupleAffineTypeNode</a>
diff --git a/docs/reference/api/doxygen/functions_u.html b/docs/reference/api/doxygen/functions_u.html
index 9051d7808e..cb5c78c74a 100644
--- a/docs/reference/api/doxygen/functions_u.html
+++ b/docs/reference/api/doxygen/functions_u.html
@@ -113,6 +113,9 @@ $(function() {
<li>Unroll()
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552">tvm::tir::ScheduleNode</a>
</li>
+<li>UnsafeSetDType()
+: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ac797a00135c910d65da297038b930ed6">tvm::tir::ScheduleNode</a>
+</li>
<li>Update()
: <a class="el" href="classtvm_1_1arith_1_1CanonicalSimplifier.html#a790c032e12c7d93e9e940297b860c509">tvm::arith::CanonicalSimplifier</a>
, <a class="el" href="classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7">tvm::arith::ConstIntBoundAnalyzer</a>
@@ -122,7 +125,7 @@ $(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#a94a93385e64ce844299729af6a573015">tvm::IRModuleNode</a>
+, <a class="el" href="classtvm_1_1IRModuleNode.html#abdd8936c6fca33ef9b7c086f8fd58f84">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_v.html b/docs/reference/api/doxygen/functions_v.html
index 9d88f5d3f0..7d67c3b706 100644
--- a/docs/reference/api/doxygen/functions_v.html
+++ b/docs/reference/api/doxygen/functions_v.html
@@ -648,7 +648,7 @@ $(function() {
: <a class="el" href="classtvm_1_1tir_1_1DataTypeLegalizer.html#a87e951cbdf97e52218f21db3fbbfaf38">tvm::tir::DataTypeLegalizer</a>
, <a class="el" href="classtvm_1_1tir_1_1IndexDataTypeRewriter.html#a8211e1dfd891b02917bd99531c8f22b2">tvm::tir::IndexDataTypeRewriter</a>
, <a class="el" href="classtvm_1_1tir_1_1StmtFunctor_3_01R_07const_01Stmt_01_6n_00_01Args_8_8_8_01args_08_4.html#a5d6146f080b95f73d41be3a2af34c934">tvm::tir::StmtFunctor< R(const Stmt &n, Args... args)></a>
-, <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a60b18d6d6bfcb692ab4a369465a175a3">tvm::tir::StmtMutator</a>
+, <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a51d66e88ec3779c117bab5ba9406091c">tvm::tir::StmtMutator</a>
, <a class="el" href="classtvm_1_1tir_1_1StmtVisitor.html#a54d994b1b7deb653e908ff5e59bb691e">tvm::tir::StmtVisitor</a>
</li>
<li>VisitStmtDefault_()
@@ -663,9 +663,9 @@ $(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#a0e715c54558934e4504c366ff803d8e1">tvm::TypeFunctor< R(const Type &n, Args...)></a>
-, <a class="el" href="classtvm_1_1TypeMutator.html#a4c7667d35d0a9a28c957165b65536c93">tvm::TypeMutator</a>
-, <a class="el" href="classtvm_1_1TypeVisitor.html#ae699be9a6ed94a635c315506e0c2a6d2">tvm::TypeVisitor</a>
+: <a class="el" href="classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html#ae4061c0c04da5b6c889842506c2d5091">tvm::TypeFunctor< R(const Type &n, Args...)></a>
+, <a class="el" href="classtvm_1_1TypeMutator.html#ad4ad7209f8789568e5e57870f0b758f0">tvm::TypeMutator</a>
+, <a class="el" href="classtvm_1_1TypeVisitor.html#a3ed59cee793514b568fa0e9cb0ca437c">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>
@@ -687,7 +687,7 @@ $(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#aea763069fe1dd6849ce0d1ec336931e0">tvm::runtime::vm::VMFunction</a>
+: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#af9d2bdcf19642c21bc4909b9e9b6196d">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/measure__candidate_8h_source.html b/docs/reference/api/doxygen/measure__candidate_8h_source.html
index d6a70daa41..f4b4dfa9c0 100644
--- a/docs/reference/api/doxygen/measure__candidate_8h_source.html
+++ b/docs/reference/api/doxygen/measure__candidate_8h_source.html
@@ -71,7 +71,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1meta__schedule_1_1MeasureCandidateNode_html_a99858dbe74082cc52938ac942523d792"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1MeasureCandidateNode.html#a99858dbe74082cc52938ac942523d792">tvm::meta_schedule::MeasureCandidateNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> measure_candidate.h:40</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1MeasureCandidateNode_html_a6891e92cac8712bb690401ed121ae7e8"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1MeasureCandidateNode.html#a6891e92cac8712bb690401ed121ae7e8">tvm::meta_schedule::MeasureCandidateNode::args_info</a></div><div class="ttdeci">Array< ArgInfo > args_info</div><div class="ttdoc">The argument information, e.g., (shape, dtype) for tensors. </div><div class="ttdef"><b>Definition:</b> measure_candidate. [...]
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:778</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:788</div></div>
<div class="ttc" id="arg__info_8h_html"><div class="ttname"><a href="arg__info_8h.html">arg_info.h</a></div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1MeasureCandidateNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1MeasureCandidateNode.html">tvm::meta_schedule::MeasureCandidateNode</a></div><div class="ttdoc">The schedule (with input shapes) to be measured. </div><div class="ttdef"><b>Definition:</b> measure_candidate.h:33</div></div>
<div class="ttc" id="array_8h_html"><div class="ttname"><a href="array_8h.html">array.h</a></div><div class="ttdoc">Runtime Array container types. </div></div>
diff --git a/docs/reference/api/doxygen/postproc_8h_source.html b/docs/reference/api/doxygen/postproc_8h_source.html
index 21b4b1d7e8..11a9768f8f 100644
--- a/docs/reference/api/doxygen/postproc_8h_source.html
+++ b/docs/reference/api/doxygen/postproc_8h_source.html
@@ -75,7 +75,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyPostprocNode_html_a3771e585727ef6dfecc502ffe57fd2a2"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyPostprocNode.html#a3771e585727ef6dfecc502ffe57fd2a2">tvm::meta_schedule::PyPostprocNode::f_apply</a></div><div class="ttdeci">FApply f_apply</div><div class="ttdoc">The packed function to the Apply function. </div><div class="ttdef"><b>Definition:</b> postproc.h:189</div></div>
<div class="ttc" id="object_8h_html_aaaa3dc5b6dc33f84b2d28f9a81267212"><div class="ttname"><a href="object_8h.html#aaaa3dc5b6dc33f84b2d28f9a81267212">TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:744</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:778</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:788</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TuneContext_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuneContext.html">tvm::meta_schedule::TuneContext</a></div><div class="ttdoc">Managed reference to TuneContextNode. </div><div class="ttdef"><b>Definition:</b> tune_context.h:95</div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1Postproc_html_a1b95aac48704d0c0740ede2040b942bb"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1Postproc.html#a1b95aac48704d0c0740ede2040b942bb">tvm::meta_schedule::Postproc::FAsString</a></div><div class="ttdeci">runtime::TypedPackedFunc< String()> FAsString</div><div class="ttdoc">Get the postprocessor function as string with name. </div><div class="ttdef"><b>Definition:</b> postproc.h:94</div></div>
diff --git a/docs/reference/api/doxygen/schedule__rule_8h_source.html b/docs/reference/api/doxygen/schedule__rule_8h_source.html
index b1c7d2943f..cc336f3d3a 100644
--- a/docs/reference/api/doxygen/schedule__rule_8h_source.html
+++ b/docs/reference/api/doxygen/schedule__rule_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="object_8h_html_aaaa3dc5b6dc33f84b2d28f9a81267212"><div class="ttname"><a href="object_8h.html#aaaa3dc5b6dc33f84b2d28f9a81267212">TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:744</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyScheduleRuleNode_html_a752192bcb5385b1ba72b7c1856c6f360"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyScheduleRuleNode.html#a752192bcb5385b1ba72b7c1856c6f360">tvm::meta_schedule::PyScheduleRuleNode::f_apply</a></div><div class="ttdeci">FApply f_apply</div><div class="ttdoc">The packed function to the Apply function. </div><div class="ttdef"><b>Definition:</b> schedule_rule.h:318</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:778</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:788</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TuneContext_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuneContext.html">tvm::meta_schedule::TuneContext</a></div><div class="ttdoc">Managed reference to TuneContextNode. </div><div class="ttdef"><b>Definition:</b> tune_context.h:95</div></div>
<div class="ttc" id="array_8h_html"><div class="ttname"><a href="array_8h.html">array.h</a></div><div class="ttdoc">Runtime Array container types. </div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
diff --git a/docs/reference/api/doxygen/search/all_11.js b/docs/reference/api/doxygen/search/all_11.js
index ec9bb67250..06ab76ad49 100644
--- a/docs/reference/api/doxygen/search/all_11.js
+++ b/docs/reference/api/doxygen/search/all_11.js
@@ -42,7 +42,7 @@ var searchData=
['parallelizevectorizeunroll',['ParallelizeVectorizeUnroll',['../classtvm_1_1meta__schedule_1_1ScheduleRule.html#a0ef9b604081db7a8bf960f3fbfd3a804',1,'tvm::meta_schedule::ScheduleRule']]],
['param_5fdevice_5findexes',['param_device_indexes',['../structtvm_1_1runtime_1_1vm_1_1VMFunction.html#afff8cae6bf6100376c4275b301a11828',1,'tvm::runtime::vm::VMFunction']]],
['params',['params',['../classtvm_1_1meta__schedule_1_1BuilderInputNode.html#a6530833b23371eaeee737cc891b160b9',1,'tvm::meta_schedule::BuilderInputNode::params()'],['../classtvm_1_1relay_1_1FunctionPatternNode.html#a0773abf2bbd77c732a3b098d68dcd92d',1,'tvm::relay::FunctionPatternNode::params()'],['../classtvm_1_1relay_1_1FunctionNode.html#a689c5078fb501798aa1d57d1825e3b5a',1,'tvm::relay::FunctionNode::params()'],['../structtvm_1_1runtime_1_1vm_1_1VMFunction.html#a6d480483112097888c7150 [...]
- ['parent',['parent',['../classtvm_1_1relay_1_1DominatorPatternNode.html#ab4720ce40ecd4f89c7eb6ff469c40375',1,'tvm::relay::DominatorPatternNode::parent()'],['../classtvm_1_1te_1_1SplitNode.html#aff313d36c09c8d93ba34aa4a251d6a9f',1,'tvm::te::SplitNode::parent()'],['../classtvm_1_1te_1_1RebaseNode.html#a4fea0a62970e2831dd92c58aee14a1f4',1,'tvm::te::RebaseNode::parent()'],['../classtvm_1_1tir_1_1StmtSRefNode.html#aa69a77c8bee12ecc0c17fe75656e392d',1,'tvm::tir::StmtSRefNode::parent()'],['.. [...]
+ ['parent',['Parent',['../classtvm_1_1tir_1_1IndexDataTypeRewriter.html#a0e7deada1e51a604e4f7bc6c8a115955',1,'tvm::tir::IndexDataTypeRewriter::Parent()'],['../classtvm_1_1tir_1_1IndexDataTypeNormalizer.html#a8d04a64a80c9fbdd28c7cb9e00c02120',1,'tvm::tir::IndexDataTypeNormalizer::Parent()'],['../classtvm_1_1relay_1_1DominatorPatternNode.html#ab4720ce40ecd4f89c7eb6ff469c40375',1,'tvm::relay::DominatorPatternNode::parent()'],['../classtvm_1_1te_1_1SplitNode.html#aff313d36c09c8d93ba34aa4a25 [...]
['parentnode',['ParentNode',['../classtvm_1_1ObjectPathNode.html#a4a06a6588b427640e2f775a6307ccab5',1,'tvm::ObjectPathNode']]],
['parse_5fauto_5fscheduler_5flayout',['parse_auto_scheduler_layout',['../namespacetvm_1_1topi.html#a6fec3a88d419cd018cf1041cf3d99204',1,'tvm::topi']]],
['parsecustomdatatype',['ParseCustomDatatype',['../namespacetvm_1_1runtime.html#ac6d167947285dff3c780bd5d01ace9b9',1,'tvm::runtime']]],
@@ -69,7 +69,7 @@ var searchData=
['path_5fto_5funderline',['path_to_underline',['../classtvm_1_1PrinterConfigNode.html#af9c9ea98dd1057e3841228292643ec5e',1,'tvm::PrinterConfigNode']]],
['pathsequal',['PathsEqual',['../classtvm_1_1ObjectPathNode.html#af3648f5578cd516a649237539467e387',1,'tvm::ObjectPathNode']]],
['pathtracingdata',['PathTracingData',['../classtvm_1_1SEqualReducer_1_1Handler.html#a3971c2653bf9bae74dd940cd80085aef',1,'tvm::SEqualReducer::Handler']]],
- ['pattern',['Pattern',['../classtvm_1_1relay_1_1Pattern.html',1,'tvm::relay::Pattern'],['../classtvm_1_1relay_1_1DFPatternCallbackNode.html#acfe3e9170d4c05ff59f3056b79ae58bb',1,'tvm::relay::DFPatternCallbackNode::pattern()'],['../classtvm_1_1relay_1_1TypePatternNode.html#a7273a1fa7c10a1c4a5f3a4d46bcd463a',1,'tvm::relay::TypePatternNode::pattern()'],['../classtvm_1_1relay_1_1ShapePatternNode.html#a77130ba4e4b1b051415a08a6c0148d30',1,'tvm::relay::ShapePatternNode::pattern()'],['../classt [...]
+ ['pattern',['Pattern',['../classtvm_1_1relay_1_1Pattern.html',1,'tvm::relay::Pattern'],['../classtvm_1_1relay_1_1Pattern.html#aba2fe5ab04ab0b56ff855cfc572b16ff',1,'tvm::relay::Pattern::Pattern()'],['../classtvm_1_1relay_1_1Pattern.html#ad2eae0030bb557fbee1b85517cd9c31e',1,'tvm::relay::Pattern::Pattern(ObjectPtr< tvm::Object > p)'],['../classtvm_1_1relay_1_1DFPatternCallbackNode.html#acfe3e9170d4c05ff59f3056b79ae58bb',1,'tvm::relay::DFPatternCallbackNode::pattern()'],['../classtvm [...]
['pattern_2eh',['pattern.h',['../pattern_8h.html',1,'']]],
['pattern_5ffunctor_2eh',['pattern_functor.h',['../pattern__functor_8h.html',1,'']]],
['pattern_5ffunctor_5fdefault',['PATTERN_FUNCTOR_DEFAULT',['../pattern__functor_8h.html#ac72a5016a4b58a73ed7e7652c7a876d7',1,'pattern_functor.h']]],
diff --git a/docs/reference/api/doxygen/search/all_13.js b/docs/reference/api/doxygen/search/all_13.js
index 609e00c3db..88b8fe226e 100644
--- a/docs/reference/api/doxygen/search/all_13.js
+++ b/docs/reference/api/doxygen/search/all_13.js
@@ -85,7 +85,7 @@ var searchData=
['registerconfigoption',['RegisterConfigOption',['../classtvm_1_1transform_1_1PassContext.html#a6f1d1040cc97320414b4690203f87919',1,'tvm::transform::PassContext']]],
['registergenericfunc',['RegisterGenericFunc',['../classtvm_1_1GenericFunc.html#a909acecbf2f34f847a34e587a4570dce',1,'tvm::GenericFunc']]],
['registerorget',['RegisterOrGet',['../classtvm_1_1OpRegEntry.html#a39a4d3e7f905eb4e29ca464bcedb05bd',1,'tvm::OpRegEntry::RegisterOrGet()'],['../classtvm_1_1relay_1_1ExecutorRegEntry.html#a03347a2b68269b853a7c0399994951ef',1,'tvm::relay::ExecutorRegEntry::RegisterOrGet()'],['../classtvm_1_1relay_1_1RuntimeRegEntry.html#ae8b479159ccd8b35b75950fcda58dd9d',1,'tvm::relay::RuntimeRegEntry::RegisterOrGet()'],['../classtvm_1_1TargetTagRegEntry.html#a07e0631600484dc0985ca62b1620461c',1,'tvm::T [...]
- ['registry',['Registry',['../classtvm_1_1runtime_1_1Registry.html',1,'tvm::runtime::Registry'],['../classtvm_1_1ReflectionVTable_1_1Registry.html',1,'tvm::ReflectionVTable::Registry'],['../classtvm_1_1ReflectionVTable_1_1Registry.html#ac8f4637640aa9dffed745303a4cfa827',1,'tvm::ReflectionVTable::Registry::Registry()'],['../structTVMMutableFuncRegistry.html#acc1fcd6554c627c1bf3b3c00e1120e9b',1,'TVMMutableFuncRegistry::registry()'],['../structTVMModule.html#a6db21005b9e983207b341e65af4c4a [...]
+ ['registry',['Registry',['../classtvm_1_1runtime_1_1Registry.html',1,'tvm::runtime::Registry'],['../classtvm_1_1ReflectionVTable_1_1Registry.html',1,'tvm::ReflectionVTable::Registry'],['../structTVMMutableFuncRegistry.html#acc1fcd6554c627c1bf3b3c00e1120e9b',1,'TVMMutableFuncRegistry::registry()'],['../structTVMModule.html#a6db21005b9e983207b341e65af4c4ab7',1,'TVMModule::registry()'],['../classtvm_1_1ReflectionVTable_1_1Registry.html#ac8f4637640aa9dffed745303a4cfa827',1,'tvm::Reflection [...]
['registry_2eh',['registry.h',['../registry_8h.html',1,'']]],
['regname',['RegName',['../namespacetvm_1_1runtime_1_1vm.html#a3bbbf700719e9dc3dda2bc25210c18ae',1,'tvm::runtime::vm']]],
['reindex',['ReIndex',['../classtvm_1_1tir_1_1ScheduleNode.html#a9e36a8a0e37a76e55068dd534e28c8c5',1,'tvm::tir::ScheduleNode']]],
@@ -127,7 +127,7 @@ var searchData=
['rendererrors',['RenderErrors',['../classtvm_1_1relay_1_1ErrorReporter.html#a79a887b4f7e46a0fcc2bb23ede14604c',1,'tvm::relay::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_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()']]],
+ ['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()']]],
['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']]],
diff --git a/docs/reference/api/doxygen/search/all_14.js b/docs/reference/api/doxygen/search/all_14.js
index deab71d5fc..6101ded893 100644
--- a/docs/reference/api/doxygen/search/all_14.js
+++ b/docs/reference/api/doxygen/search/all_14.js
@@ -101,7 +101,7 @@ var searchData=
['selectshashreduce_3c_20t_2c_20traitname_2c_20false_20_3e',['SelectSHashReduce< T, TraitName, false >',['../structtvm_1_1detail_1_1SelectSHashReduce_3_01T_00_01TraitName_00_01false_01_4.html',1,'tvm::detail']]],
['selectvisitattrs',['SelectVisitAttrs',['../structtvm_1_1detail_1_1SelectVisitAttrs.html',1,'tvm::detail']]],
['selectvisitattrs_3c_20t_2c_20traitname_2c_20false_20_3e',['SelectVisitAttrs< T, TraitName, false >',['../structtvm_1_1detail_1_1SelectVisitAttrs_3_01T_00_01TraitName_00_01false_01_4.html',1,'tvm::detail']]],
- ['self',['Self',['../classtvm_1_1runtime_1_1InplaceArrayBase.html#ae447f7c7a742fb3f5613a632706509df',1,'tvm::runtime::InplaceArrayBase::Self()'],['../classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a5bac4439279428fb3c0d44aa6b1cc798',1,'tvm::runtime::MapNode::iterator::self()']]],
+ ['self',['self',['../classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a5bac4439279428fb3c0d44aa6b1cc798',1,'tvm::runtime::MapNode::iterator::self()'],['../classtvm_1_1runtime_1_1InplaceArrayBase.html#ae447f7c7a742fb3f5613a632706509df',1,'tvm::runtime::InplaceArrayBase::Self()']]],
['sendbodychunk',['SendBodyChunk',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#a37b77101825145283cced6cd05eb502c',1,'tvm::runtime::micro_rpc::Session']]],
['sendmessage',['SendMessage',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#a6e540521a7e9188564da712c0641619c',1,'tvm::runtime::micro_rpc::Session']]],
['seq',['seq',['../classtvm_1_1tir_1_1SeqStmtNode.html#a0e548955529d35c56e646fcaac38f865',1,'tvm::tir::SeqStmtNode']]],
@@ -337,7 +337,7 @@ 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']]],
['start_5fprofile_5fintrinsic',['start_profile_intrinsic',['../namespacetvm_1_1tir_1_1builtin.html#aa63c16281d1010a82a06eb771268b4e2',1,'tvm::tir::builtin']]],
['startcall',['StartCall',['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#a1fe322f7ba92be44d7e7c8cb184f3833',1,'tvm::runtime::profiling::Profiler']]],
@@ -382,7 +382,7 @@ var searchData=
['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 [...]
['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']]],
diff --git a/docs/reference/api/doxygen/search/all_15.js b/docs/reference/api/doxygen/search/all_15.js
index 0942d306e7..ba5cfafd33 100644
--- a/docs/reference/api/doxygen/search/all_15.js
+++ b/docs/reference/api/doxygen/search/all_15.js
@@ -77,7 +77,7 @@ 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,'']]],
@@ -96,7 +96,7 @@ 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_1tir_1_1TensorIntrinNode.html',1,'tvm::tir::TensorIntrinNode'],['../classtvm_1_1te_1_1TensorIntrinNode.html',1,'tvm::te::TensorIntrinNode'],['../classtvm_1_1te_1_1TensorIntrinNode.html#ad59e7f2b881fc798a8c64fd3959f929c',1,'tvm::te::TensorIntrinNode::TensorIntrinNode()']]],
- ['tensorize',['Tensorize',['../classtvm_1_1tir_1_1ScheduleNode.html#a66983e2dde6aeb18b443616398fff8bf',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &loop_rv, const String &intrin, bool preserve_unit_iters=true)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#afa67abdb51145a49d42cd1464429d928',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &block_rv, const String &intrin, bool preserve_unit_iters=true)=0'],['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c06 [...]
+ ['tensorize',['tensorize',['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a66983e2dde6aeb18b443616398fff8bf',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &loop_rv, const String &intrin, bool preserve_unit_iters=true)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#afa67abdb51145a49d42cd1464429d928',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &block_rv, const String & [...]
['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()']]],
diff --git a/docs/reference/api/doxygen/search/all_16.js b/docs/reference/api/doxygen/search/all_16.js
index 25a5cd9d2f..92f4bbae88 100644
--- a/docs/reference/api/doxygen/search/all_16.js
+++ b/docs/reference/api/doxygen/search/all_16.js
@@ -40,7 +40,7 @@ var searchData=
['unionregion',['UnionRegion',['../namespacetvm_1_1arith.html#ad27c4f216e41eb8e81296fb7ec4b9453',1,'tvm::arith']]],
['unionregionlowerbound',['UnionRegionLowerBound',['../namespacetvm_1_1arith.html#a4c3dedfa4cba4ad39c953eb51eb83e4d',1,'tvm::arith']]],
['unipolar',['unipolar',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a7e0ad68dce226079b769a678aa01dc49',1,'tvm::relay::BinaryConv2DAttrs::unipolar()'],['../structtvm_1_1relay_1_1BinaryDenseAttrs.html#af21cdb9dac67ab9ecea5a19642658d8a',1,'tvm::relay::BinaryDenseAttrs::unipolar()']]],
- ['unique',['unique',['../classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7',1,'tvm::runtime::Object::unique()'],['../classtvm_1_1runtime_1_1ObjectPtr.html#af95c6c6fcd89da0f62b93f1167b72314',1,'tvm::runtime::ObjectPtr::unique()'],['../classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7',1,'tvm::runtime::ObjectRef::unique()'],['../classtvm_1_1VirtualDeviceCache.html#a25ba1351484aa58a2cc7cef8f8e4423c',1,'tvm::VirtualDeviceCache::Unique()']]],
+ ['unique',['Unique',['../classtvm_1_1VirtualDeviceCache.html#a25ba1351484aa58a2cc7cef8f8e4423c',1,'tvm::VirtualDeviceCache::Unique()'],['../classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7',1,'tvm::runtime::Object::unique()'],['../classtvm_1_1runtime_1_1ObjectPtr.html#af95c6c6fcd89da0f62b93f1167b72314',1,'tvm::runtime::ObjectPtr::unique()'],['../classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7',1,'tvm::runtime::ObjectRef::unique()']]],
['uniqueattrs',['UniqueAttrs',['../structtvm_1_1relay_1_1UniqueAttrs.html',1,'tvm::relay']]],
['uniqueglobalfor',['UniqueGlobalFor',['../classtvm_1_1GlobalVarSupplyNode.html#af67bad5d9d93381c440a7886cbef430a',1,'tvm::GlobalVarSupplyNode']]],
['unit_5fbits',['unit_bits',['../classtvm_1_1MemoryInfoNode.html#a505c2f2dd0dd0c28a12b9113e2176a8d',1,'tvm::MemoryInfoNode']]],
@@ -51,6 +51,7 @@ var searchData=
['unravel_5findex',['unravel_index',['../namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e',1,'tvm::topi']]],
['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']]],
+ ['unsafesetdtype',['UnsafeSetDType',['../classtvm_1_1tir_1_1ScheduleNode.html#ac797a00135c910d65da297038b930ed6',1,'tvm::tir::ScheduleNode']]],
['update',['update',['../classtvm_1_1te_1_1ScanOpNode.html#ace2bf7e43cd4197324ec6363626fc60a',1,'tvm::te::ScanOpNode::update()'],['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::a [...]
['update_5ffunc',['update_func',['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#ade9364c152a36501d4f24fa4f0111519',1,'tvm::auto_scheduler::PythonBasedModelNode']]],
['updatecostmodel',['UpdateCostModel',['../classtvm_1_1meta__schedule_1_1MeasureCallback.html#afdf5503c6e6f53767de132d91a7b53f9',1,'tvm::meta_schedule::MeasureCallback']]],
diff --git a/docs/reference/api/doxygen/search/all_17.js b/docs/reference/api/doxygen/search/all_17.js
index 231ce224aa..974631a51a 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_5fremap_5f',['var_remap_',['../classtvm_1_1tir_1_1DataTypeLegalizer.html#a1de0d50699d7d15618b19d2cb7fadb35',1,'tvm::tir::DataTypeLegalizer']]],
['variableinfo',['VariableInfo',['../structtvm_1_1script_1_1printer_1_1IRDocsifierNode_1_1VariableInfo.html',1,'tvm::script::printer::IRDocsifierNode']]],
diff --git a/docs/reference/api/doxygen/search/all_18.js b/docs/reference/api/doxygen/search/all_18.js
index 08811415b9..9623990506 100644
--- a/docs/reference/api/doxygen/search/all_18.js
+++ b/docs/reference/api/doxygen/search/all_18.js
@@ -34,7 +34,7 @@ var searchData=
['withfields',['WithFields',['../namespacetvm_1_1relay.html#acd80501d29e4d951be6746c79934a70c',1,'tvm::relay::WithFields(Clause clause, Optional< Pattern > opt_lhs=Optional< Pattern >(), Optional< Expr > opt_rhs=Optional< Expr >())'],['../namespacetvm_1_1relay.html#adb39b46f86b66a5e7252f6d9102deb7b',1,'tvm::relay::WithFields(Match match, Optional< Expr > opt_data=Optional< Expr >(), Optional< Array< Clause >> opt_clauses=Optional< Arra [...]
['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_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',['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_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::WorkloadEqual'],['../structtvm_1_1meta__schedule_1_1WorkloadEqual.html#a49b0e137a01a278469ff63729afae804',1,'tvm::meta_schedule::WorkloadEqual::WorkloadEqual()']]],
['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 884b8229db..1082ae16d9 100644
--- a/docs/reference/api/doxygen/search/all_a.js
+++ b/docs/reference/api/doxygen/search/all_a.js
@@ -177,7 +177,7 @@ var searchData=
['intvalue',['IntValue',['../classtvm_1_1Integer.html#abae4eff906166502c2a982e8a121d81d',1,'tvm::Integer']]],
['invalid_5fto_5fbottom',['invalid_to_bottom',['../structtvm_1_1relay_1_1NonMaximumSuppressionAttrs.html#a51ab0634c017ed9a2fbf8706f22365dc',1,'tvm::relay::NonMaximumSuppressionAttrs']]],
['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::Inverse()'],['../structtvm_1_1relay_1_1DFTAttrs.html#a51fa18ceac3ad908a2f9fdf8ebbe512f',1,'tvm::relay::DFTAttrs::inverse()']]],
+ ['inverse',['inverse',['../structtvm_1_1relay_1_1DFTAttrs.html#a51fa18ceac3ad908a2f9fdf8ebbe512f',1,'tvm::relay::DFTAttrs::inverse()'],['../classtvm_1_1tir_1_1IndexMap.html#a5363f3897623b7854aed24b2fd657f5a',1,'tvm::tir::IndexMap::Inverse()']]],
['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']]],
diff --git a/docs/reference/api/doxygen/search/all_e.js b/docs/reference/api/doxygen/search/all_e.js
index 4b7aa96b53..14f32f6912 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_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',['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_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_12.js b/docs/reference/api/doxygen/search/functions_12.js
index 698c235f67..0d0fef0b8d 100644
--- a/docs/reference/api/doxygen/search/functions_12.js
+++ b/docs/reference/api/doxygen/search/functions_12.js
@@ -62,7 +62,7 @@ var searchData=
['rendererrors',['RenderErrors',['../classtvm_1_1relay_1_1ErrorReporter.html#a79a887b4f7e46a0fcc2bb23ede14604c',1,'tvm::relay::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_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()']]],
+ ['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()']]],
['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']]],
diff --git a/docs/reference/api/doxygen/search/functions_14.js b/docs/reference/api/doxygen/search/functions_14.js
index 68aba19f8a..4729b0069c 100644
--- a/docs/reference/api/doxygen/search/functions_14.js
+++ b/docs/reference/api/doxygen/search/functions_14.js
@@ -21,7 +21,7 @@ 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_1tir_1_1ScheduleNode.html#a66983e2dde6aeb18b443616398fff8bf',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &loop_rv, const String &intrin, bool preserve_unit_iters=true)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#afa67abdb51145a49d42cd1464429d928',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &block_rv, const String &intrin, bool preserve_unit_iters=true)=0'],['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c06 [...]
+ ['tensorize',['tensorize',['../classtvm_1_1te_1_1Stage.html#ab5fe485e1d730c36b096c060b8d2ef9d',1,'tvm::te::Stage::tensorize()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a66983e2dde6aeb18b443616398fff8bf',1,'tvm::tir::ScheduleNode::Tensorize(const LoopRV &loop_rv, const String &intrin, bool preserve_unit_iters=true)=0'],['../classtvm_1_1tir_1_1ScheduleNode.html#afa67abdb51145a49d42cd1464429d928',1,'tvm::tir::ScheduleNode::Tensorize(const BlockRV &block_rv, const String & [...]
['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 52aeb91d89..e49b0303fe 100644
--- a/docs/reference/api/doxygen/search/functions_15.js
+++ b/docs/reference/api/doxygen/search/functions_15.js
@@ -37,13 +37,14 @@ var searchData=
['unionlowerbound',['UnionLowerBound',['../namespacetvm_1_1arith.html#ab22d7fd95abb5fa372843a40e19d80c5',1,'tvm::arith']]],
['unionregion',['UnionRegion',['../namespacetvm_1_1arith.html#ad27c4f216e41eb8e81296fb7ec4b9453',1,'tvm::arith']]],
['unionregionlowerbound',['UnionRegionLowerBound',['../namespacetvm_1_1arith.html#a4c3dedfa4cba4ad39c953eb51eb83e4d',1,'tvm::arith']]],
- ['unique',['unique',['../classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7',1,'tvm::runtime::Object::unique()'],['../classtvm_1_1runtime_1_1ObjectPtr.html#af95c6c6fcd89da0f62b93f1167b72314',1,'tvm::runtime::ObjectPtr::unique()'],['../classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7',1,'tvm::runtime::ObjectRef::unique()'],['../classtvm_1_1VirtualDeviceCache.html#a25ba1351484aa58a2cc7cef8f8e4423c',1,'tvm::VirtualDeviceCache::Unique()']]],
+ ['unique',['Unique',['../classtvm_1_1VirtualDeviceCache.html#a25ba1351484aa58a2cc7cef8f8e4423c',1,'tvm::VirtualDeviceCache::Unique()'],['../classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7',1,'tvm::runtime::Object::unique()'],['../classtvm_1_1runtime_1_1ObjectPtr.html#af95c6c6fcd89da0f62b93f1167b72314',1,'tvm::runtime::ObjectPtr::unique()'],['../classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7',1,'tvm::runtime::ObjectRef::unique()']]],
['uniqueglobalfor',['UniqueGlobalFor',['../classtvm_1_1GlobalVarSupplyNode.html#af67bad5d9d93381c440a7886cbef430a',1,'tvm::GlobalVarSupplyNode']]],
['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_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']]],
+ ['unsafesetdtype',['UnsafeSetDType',['../classtvm_1_1tir_1_1ScheduleNode.html#ac797a00135c910d65da297038b930ed6',1,'tvm::tir::ScheduleNode']]],
['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']]],
['updateiters',['UpdateIters',['../classtvm_1_1auto__scheduler_1_1AttachMap.html#ab45b991ef2bcfb1bc191601aac42e778',1,'tvm::auto_scheduler::AttachMap']]],
diff --git a/docs/reference/api/doxygen/search/functions_d.js b/docs/reference/api/doxygen/search/functions_d.js
index 87821c714d..faf0060ebc 100644
--- a/docs/reference/api/doxygen/search/functions_d.js
+++ b/docs/reference/api/doxygen/search/functions_d.js
@@ -38,7 +38,7 @@ 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_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',['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_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/tir_2schedule_2schedule_8h_source.html b/docs/reference/api/doxygen/tir_2schedule_2schedule_8h_source.html
index bea63dfe1d..e7bd35fe6d 100644
--- a/docs/reference/api/doxygen/tir_2schedule_2schedule_8h_source.html
+++ b/docs/reference/api/doxygen/tir_2schedule_2schedule_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">schedule.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="tir_2schedule_2schedule_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 [...]
+<a href="tir_2schedule_2schedule_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 [...]
<div class="ttc" id="namespacetvm_1_1script_1_1ir__builder_1_1tir_html_acd41556b0c4088d0f309ef5495aaebe3"><div class="ttname"><a href="namespacetvm_1_1script_1_1ir__builder_1_1tir.html#acd41556b0c4088d0f309ef5495aaebe3">tvm::script::ir_builder::tir::Unroll</a></div><div class="ttdeci">ForFrame Unroll(PrimExpr start, PrimExpr stop, Optional< Map< String, ObjectRef >> annotations=NullOpt)</div><div class="ttdoc">The unrolled For statement. </div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StmtNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtNode.html">tvm::tir::StmtNode</a></div><div class="ttdoc">Base node of all statements. </div><div class="ttdef"><b>Definition:</b> stmt.h:38</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BlockRVNode_html_af90b398c502892d19ff3bdf6463d32ab"><div class="ttname"><a href="classtvm_1_1tir_1_1BlockRVNode.html#af90b398c502892d19ff3bdf6463d32ab">tvm::tir::BlockRVNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> schedule.h:53</div></div>
@@ -84,7 +84,7 @@ $(function() {
<div class="ttc" id="object_8h_html_aaaa3dc5b6dc33f84b2d28f9a81267212"><div class="ttname"><a href="object_8h.html#aaaa3dc5b6dc33f84b2d28f9a81267212">TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:744</div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_a9ae244600a5e56c4adc9faf6d88f931e"><div class="ttname"><a href="namespacetvm_1_1tir.html#a9ae244600a5e56c4adc9faf6d88f931e">tvm::tir::ScheduleErrorRenderLevel</a></div><div class="ttdeci">ScheduleErrorRenderLevel</div><div class="ttdoc">The level of detailed error message rendering. </div><div class="ttdef"><b>Definition:</b> schedule.h:31</div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_a9ae244600a5e56c4adc9faf6d88f931ead6733547bb237ce06cddf96357f1b66b"><div class="ttname"><a href="namespacetvm_1_1tir.html#a9ae244600a5e56c4adc9faf6d88f931ead6733547bb237ce06cddf96357f1b66b">tvm::tir::ScheduleErrorRenderLevel::kDetail</a></div><div class="ttdoc">Render a detailed error message. </div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:778</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:788</div></div>
<div class="ttc" id="index__map_8h_html"><div class="ttname"><a href="index__map_8h.html">index_map.h</a></div><div class="ttdoc">Defines a remapping of buffer indices. </div></div>
<div class="ttc" id="classtvm_1_1support_1_1LinearCongruentialEngine_html_a4d3a3a94a3f3d2dfab4b5ccb1a7e97de"><div class="ttname"><a href="classtvm_1_1support_1_1LinearCongruentialEngine.html#a4d3a3a94a3f3d2dfab4b5ccb1a7e97de">tvm::support::LinearCongruentialEngine::TRandState</a></div><div class="ttdeci">int64_t TRandState</div><div class="ttdef"><b>Definition:</b> random_engine.h:46</div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
diff --git a/docs/reference/api/doxygen/trace_8h_source.html b/docs/reference/api/doxygen/trace_8h_source.html
index 1664831a6e..b0c52fa523 100644
--- a/docs/reference/api/doxygen/trace_8h_source.html
+++ b/docs/reference/api/doxygen/trace_8h_source.html
@@ -76,7 +76,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_html_a75918aeef1136f9d6308556902d5bcae"><div class="ttname"><a href="namespacetvm_1_1tir.html#a75918aeef1136f9d6308556902d5bcae">tvm::tir::FTraceDecisionProvider</a></div><div class="ttdeci">runtime::TypedPackedFunc< ObjectRef(const Instruction &inst, const Array< ObjectRef > &inputs, const Array< ObjectRef > &attrs, const Optional< ObjectRef > &decision)> FTraceDecisionProvider</div><div class="ttdoc">A cal [...]
<div class="ttc" id="instruction_8h_html"><div class="ttname"><a href="instruction_8h.html">instruction.h</a></div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:778</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:788</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1TraceNode_html_ad6c859ed32b1e2ae076355eda37df0a2"><div class="ttname"><a href="classtvm_1_1tir_1_1TraceNode.html#ad6c859ed32b1e2ae076355eda37df0a2">tvm::tir::TraceNode::insts</a></div><div class="ttdeci">Array< Instruction > insts</div><div class="ttdoc">The instructions invoked so far in the program execution. </div><div class="ttdef"><b>Definition:</b> trace.h:61</div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1TraceNode_html_a764346045e536fa26b56c9e140de8e7b"><div class="ttname"><a href="classtvm_1_1tir_1_1TraceNode.html#a764346045e536fa26b56c9e140de8e7b">tvm::tir::TraceNode::ApplyToSchedule</a></div><div class="ttdeci">void ApplyToSchedule(Schedule sch, bool remove_postproc, FTraceDecisionProvider decision_provider=nullptr) const</div><div class="ttdoc">Apply the trace to a TensorIR schedule. </div></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 0aa767e297..0dbf9faafd 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1621,7 +1621,7 @@ 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>
@@ -1905,7 +1905,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index be8ad21aa0..1e3b54c11d 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -5854,42 +5854,45 @@ preserve the semantics of computation. Some example of schedules:
<td><p>Set alignment requirement for specific dimension such that stride[axis] == k * factor + offset for some k.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.set_scope" title="tvm.tir.Schedule.set_scope"><code class="xref py py-obj docutils literal notranslate"><span class="pre">set_scope</span></code></a>(block, buffer_index, storage_scope)</p></td>
-<td><p>Set the storage scope of a buffer, where the buffer is specified by the a block and a write-index</p></td>
+<td><p>Set the storage scope of a buffer, where the buffer is specified by the a block and a write-index.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.blockize" title="tvm.tir.Schedule.blockize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">blockize</span></code></a>(loop[, preserve_unit_iters])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.unsafe_set_dtype" title="tvm.tir.Schedule.unsafe_set_dtype"><code class="xref py py-obj docutils literal notranslate"><span class="pre">unsafe_set_dtype</span></code></a>(block, buffer_index, dtype)</p></td>
+<td><p>Set the data type of a buffer, where the buffer is specified by the a block and write-index.</p></td>
+</tr>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.blockize" title="tvm.tir.Schedule.blockize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">blockize</span></code></a>(loop[, preserve_unit_iters])</p></td>
<td><p>Convert the subtree rooted at a specific loop into a block.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.tensorize" title="tvm.tir.Schedule.tensorize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tensorize</span></code></a>(block_or_loop, tensor_intrin[, ...])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.tensorize" title="tvm.tir.Schedule.tensorize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tensorize</span></code></a>(block_or_loop, tensor_intrin[, ...])</p></td>
<td><p>Tensorize the computation enclosed by loop with the tensor intrinsic.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.annotate" title="tvm.tir.Schedule.annotate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">annotate</span></code></a>(block_or_loop, ann_key, ann_val)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.annotate" title="tvm.tir.Schedule.annotate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">annotate</span></code></a>(block_or_loop, ann_key, ann_val)</p></td>
<td><p>Annotate a block/loop with a key value pair</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.unannotate" title="tvm.tir.Schedule.unannotate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">unannotate</span></code></a>(block_or_loop, ann_key)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.unannotate" title="tvm.tir.Schedule.unannotate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">unannotate</span></code></a>(block_or_loop, ann_key)</p></td>
<td><p>Unannotate a block/loop's annotation with key ann_key</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.transform_layout" title="tvm.tir.Schedule.transform_layout"><code class="xref py py-obj docutils literal notranslate"><span class="pre">transform_layout</span></code></a>(block, buffer, index_map[, ...])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.transform_layout" title="tvm.tir.Schedule.transform_layout"><code class="xref py py-obj docutils literal notranslate"><span class="pre">transform_layout</span></code></a>(block, buffer, index_map[, ...])</p></td>
<td><p>Apply a transformation represented by IndexMap to buffer</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.transform_block_layout" title="tvm.tir.Schedule.transform_block_layout"><code class="xref py py-obj docutils literal notranslate"><span class="pre">transform_block_layout</span></code></a>(block, index_map)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.transform_block_layout" title="tvm.tir.Schedule.transform_block_layout"><code class="xref py py-obj docutils literal notranslate"><span class="pre">transform_block_layout</span></code></a>(block, index_map)</p></td>
<td><p>Apply a transformation represented by IndexMap to block</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.set_axis_separator" title="tvm.tir.Schedule.set_axis_separator"><code class="xref py py-obj docutils literal notranslate"><span class="pre">set_axis_separator</span></code></a>(block, buffer, ...)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.set_axis_separator" title="tvm.tir.Schedule.set_axis_separator"><code class="xref py py-obj docutils literal notranslate"><span class="pre">set_axis_separator</span></code></a>(block, buffer, ...)</p></td>
<td><p>Set the axis separator of a buffer, where the buffer is specified by a block and a read or write index.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.decompose_padding" title="tvm.tir.Schedule.decompose_padding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">decompose_padding</span></code></a>(block, loop)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.decompose_padding" title="tvm.tir.Schedule.decompose_padding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">decompose_padding</span></code></a>(block, loop)</p></td>
<td><p>Decompose a block of padding computation pattern into two separate blocks.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.can_decompose_padding" title="tvm.tir.Schedule.can_decompose_padding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">can_decompose_padding</span></code></a>(block, loop)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.can_decompose_padding" title="tvm.tir.Schedule.can_decompose_padding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">can_decompose_padding</span></code></a>(block, loop)</p></td>
<td><p>Check whether the block match padding pattern and can be decomposed.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.pad_einsum" title="tvm.tir.Schedule.pad_einsum"><code class="xref py py-obj docutils literal notranslate"><span class="pre">pad_einsum</span></code></a>(block, padding)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.pad_einsum" title="tvm.tir.Schedule.pad_einsum"><code class="xref py py-obj docutils literal notranslate"><span class="pre">pad_einsum</span></code></a>(block, padding)</p></td>
<td><p>Pad the computation of Einsum.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.rolling_buffer" title="tvm.tir.Schedule.rolling_buffer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">rolling_buffer</span></code></a>(block, write_buffer_index)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.rolling_buffer" title="tvm.tir.Schedule.rolling_buffer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">rolling_buffer</span></code></a>(block, write_buffer_index)</p></td>
<td><p>Compute the target buffer via rolling buffering, select the outermost rollable axis with a positive bound overlap that appears in the block's ancestor loops as <cite>rolling axis</cite>, fold and circularize the buffer along the rolling dimension, append block predicate to avoid recomputing overlapping elements.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.enter_postproc" title="tvm.tir.Schedule.enter_postproc"><code class="xref py py-obj docutils literal notranslate"><span class="pre">enter_postproc</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.enter_postproc" title="tvm.tir.Schedule.enter_postproc"><code class="xref py py-obj docutils literal notranslate"><span class="pre">enter_postproc</span></code></a>()</p></td>
<td><p>A no-op that marks the start of postprocessing phase of scheduling</p></td>
</tr>
</tbody>
@@ -7600,7 +7603,7 @@ to avoid bank conflict for thread access on higher dimension in GPU shared memor
<dt class="sig sig-object py" id="tvm.tir.Schedule.set_scope">
<span class="sig-name descname"><span class="pre">set_scope</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">block</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">tvm.tir.schedule.schedule.BlockRV</span><span class="p"><span class="pre">,</span> </span><a class="reference external" href="https://docs.python.org [...]
<dd><p>Set the storage scope of a buffer, where the buffer is
-specified by the a block and a write-index</p>
+specified by the a block and a write-index.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
@@ -7653,7 +7656,70 @@ specified by the a block and a write-index</p>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
-<p>Set_scope requires the buffer to be an intermediate buffer defined via <cite>alloc_buffer</cite>.</p>
+<p><cite>set_scope</cite> requires the buffer to be an intermediate buffer defined via <cite>alloc_buffer</cite>.</p>
+</div>
+</dd></dl>
+
+<dl class="py method">
+<dt class="sig sig-object py" id="tvm.tir.Schedule.unsafe_set_dtype">
+<span class="sig-name descname"><span class="pre">unsafe_set_dtype</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">block</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">tvm.tir.schedule.schedule.BlockRV</span><span class="p"><span class="pre">,</span> </span><a class="reference external" href="https://docs.pyt [...]
+<dd><p>Set the data type of a buffer, where the buffer is
+specified by the a block and write-index.</p>
+<p>This schedule primitive is unsafe and may change the correctness of program because of
+type conversion, please use with caution.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>block</strong> (<em>Union</em><em>[</em><em>BlockRV</em><em>, </em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.11)"><em>str</em></a><em>]</em>) – The producer block of the buffer</p></li>
+<li><p><strong>buffer_index</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.11)"><em>int</em></a>) – The index of the buffer in block’s write region</p></li>
+<li><p><strong>dtype</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.11)"><em>str</em></a>) – The data type to be set</p></li>
+</ul>
+</dd>
+</dl>
+<p class="rubric">Examples</p>
+<p>Before set_dtype, in TensorIR, the IR is:</p>
+<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="nd">@T</span><span class="o">.</span><span class="n">prim_func</span>
+<span class="k">def</span> <span class="nf">before_set_dtype</span><span class="p">(</span>
+ <span class="n">A</span><span class="p">:</span> <span class="n">T</span><span class="o">.</span><span class="n">Buffer</span><span class="p">((</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">),</span> <span class="s2">"float32"</span><span class="p">),</span> <span class="n">C</span><span class="p">:</span> <span class="n">T</span><span class="o">.</span><span class="n">Buffer</span><span class="p">((</span><span class= [...]
+<span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
+ <span class="n">B</span> <span class="o">=</span> <span class="n">T</span><span class="o">.</span><span class="n">alloc_buffer</span><span class="p">((</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">"float32"</span><span class="p">)</span>
+
+ <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">T</span><span class="o">.</span><span class="n">grid</span><span class="p">(</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">):</span>
+ <span class="k">with</span> <span class="n">T</span><span class="o">.</span><span class="n">block</span><span class="p">(</span><span class="s2">"B"</span><span class="p">):</span>
+ <span class="n">vi</span><span class="p">,</span> <span class="n">vj</span> <span class="o">=</span> <span class="n">T</span><span class="o">.</span><span class="n">axis</span><span class="o">.</span><span class="n">remap</span><span class="p">(</span><span class="s2">"SS"</span><span class="p">,</span> <span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">])</span>
+ <span class="n">B</span><span class="p">[</span><span class="n">vi</span><span class="p">,</span> <span class="n">vj</span><span class="p">]</span> <span class="o">=</span> <span class="n">A</span><span class="p">[</span><span class="n">vi</span><span class="p">,</span> <span class="n">vj</span><span class="p">]</span> <span class="o">*</span> <span class="mf">2.0</span>
+ <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">T</span><span class="o">.</span><span class="n">grid</span><span class="p">(</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">):</span>
+ <span class="k">with</span> <span class="n">T</span><span class="o">.</span><span class="n">block</span><span class="p">(</span><span class="s2">"C"</span><span class="p">):</span>
+ <span class="n">vi</span><span class="p">,</span> <span class="n">vj</span> <span class="o">=</span> <span class="n">T</span><span class="o">.</span><span class="n">axis</span><span class="o">.</span><span class="n">remap</span><span class="p">(</span><span class="s2">"SS"</span><span class="p">,</span> <span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">]</span>
+ <span class="n">C</span><span class="p">[</span><span class="n">vi</span><span class="p">,</span> <span class="n">vj</span><span class="p">]</span> <span class="o">=</span> <span class="n">B</span><span class="p">[</span><span class="n">vi</span><span class="p">,</span> <span class="n">vj</span><span class="p">]</span> <span class="o">+</span> <span class="mf">1.0</span>
+</pre></div>
+</div>
+<p>Create the schedule and do set_dtype:</p>
+<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">sch</span> <span class="o">=</span> <span class="n">tir</span><span class="o">.</span><span class="n">Schedule</span><span class="p">(</span><span class="n">before_set_dtype</span><span class="p">)</span>
+<span class="n">sch</span><span class="o">.</span><span class="n">set_dtype</span><span class="p">(</span><span class="s2">"B"</span><span class="p">,</span> <span class="n">buffer_index</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">"float16"</span><span class="p">)</span>
+<span class="nb">print</span><span class="p">(</span><span class="n">sch</span><span class="o">.</span><span class="n">mod</span><span class="p">[</span><span class="s2">"main"</span><span class="p">]</span><span class="o">.</span><span class="n">script</span><span class="p">())</span>
+</pre></div>
+</div>
+<p>After applying set_dtype, the IR becomes:</p>
+<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="nd">@T</span><span class="o">.</span><span class="n">prim_func</span>
+<span class="k">def</span> <span class="nf">after_set_dtype</span><span class="p">(</span>
+ <span class="n">A</span><span class="p">:</span> <span class="n">T</span><span class="o">.</span><span class="n">Buffer</span><span class="p">((</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">),</span> <span class="s2">"float32"</span><span class="p">),</span> <span class="n">C</span><span class="p">:</span> <span class="n">T</span><span class="o">.</span><span class="n">Buffer</span><span class="p">((</span><span class= [...]
+<span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
+ <span class="n">B</span> <span class="o">=</span> <span class="n">T</span><span class="o">.</span><span class="n">alloc_buffer</span><span class="p">((</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">"float16"</span><span class="p">)</span>
+
+ <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">T</span><span class="o">.</span><span class="n">grid</span><span class="p">(</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">):</span>
+ <span class="k">with</span> <span class="n">T</span><span class="o">.</span><span class="n">block</span><span class="p">(</span><span class="s2">"B"</span><span class="p">):</span>
+ <span class="n">vi</span><span class="p">,</span> <span class="n">vj</span> <span class="o">=</span> <span class="n">T</span><span class="o">.</span><span class="n">axis</span><span class="o">.</span><span class="n">remap</span><span class="p">(</span><span class="s2">"SS"</span><span class="p">,</span> <span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">])</span>
+ <span class="n">B</span><span class="p">[</span><span class="n">vi</span><span class="p">,</span> <span class="n">vj</span><span class="p">]</span> <span class="o">=</span> <span class="n">T</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">A</span><span class="p">[</span><span class="n">vi</span><span class="p">,</span> <span class="n">vj</span><span class="p">]</span> <span class="o">*</span> <span class="mf">2.0</span><span cl [...]
+ <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">T</span><span class="o">.</span><span class="n">grid</span><span class="p">(</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">):</span>
+ <span class="k">with</span> <span class="n">T</span><span class="o">.</span><span class="n">block</span><span class="p">(</span><span class="s2">"C"</span><span class="p">):</span>
+ <span class="n">vi</span><span class="p">,</span> <span class="n">vj</span> <span class="o">=</span> <span class="n">T</span><span class="o">.</span><span class="n">axis</span><span class="o">.</span><span class="n">remap</span><span class="p">(</span><span class="s2">"SS"</span><span class="p">,</span> <span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">]</span>
+ <span class="n">C</span><span class="p">[</span><span class="n">vi</span><span class="p">,</span> <span class="n">vj</span><span class="p">]</span> <span class="o">=</span> <span class="n">T</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">B</span><span class="p">[</span><span class="n">vi</span><span class="p">,</span> <span class="n">vj</span><span class="p">],</span> <span class="s2">"float32"</span><span class="p"> [...]
+</pre></div>
+</div>
+<div class="admonition note">
+<p class="admonition-title">Note</p>
+<p><cite>set_dtype</cite> requires the buffer to be an intermediate buffer defined via <cite>alloc_buffer</cite>.</p>
</div>
</dd></dl>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 7a9389c3f4..4885b97dab 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/0c2dd4728/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L45">rpc_server.ts:45</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/0c2dd4728/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L45">rpc_server.ts:45</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/0c2dd4728/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L44">rpc_server.ts:44</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/0c2dd4728/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L65">rpc_server.ts:65</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/0c2dd4728/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L51">rpc_server.ts:51</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/0c2dd4728/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L59">rpc_server.ts:59</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 bf38564ffc..489dd90643 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/0c2dd4728/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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 69e75b9bb7..c87d07b699 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/0c2dd4728/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L359">runtime.ts:359</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/0c2dd4728/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L357">runtime.ts:357</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/0c2dd4728/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L355">runtime.ts:355</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/0c2dd4728/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L359">runtime.ts:359</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/0c2dd4728/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L376">runtime.ts:376</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/0c2dd4728/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L367">runtime.ts:367</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 d6331dad98..d558ffd1d9 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/0c2dd4728/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L299">runtime.ts:299</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/0c2dd4728/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L297">runtime.ts:297</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/0c2dd4728/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L295">runtime.ts:295</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/0c2dd4728/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L320">runtime.ts:320</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/0c2dd4728/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L327">runtime.ts:327</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 442b72eedc..ec2a808b47 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/0c2dd4728/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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 219ca2e332..6c948f685f 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/0c2dd4728/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L50">runtime.ts:50</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/0c2dd4728/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L47">runtime.ts:47</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/0c2dd4728/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L46">runtime.ts:46</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/0c2dd4728/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L45">runtime.ts:45</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/0c2dd4728/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L48">runtime.ts:48</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/0c2dd4728/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L77">runtime.ts:77</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/0c2dd4728/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L67">runtime.ts:67</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/0c2dd4728/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L85">runtime.ts:85</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/0c2dd4728/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L96">runtime.ts:96</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/0c2dd4728/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L73">runtime.ts:73</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/instance.html b/docs/reference/api/typedoc/classes/instance.html
index e8ec645fe1..01a75ec7ee 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<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/0c2dd4728/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<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/0c2dd4728/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L957">runtime.ts:957</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 8b34eb944e..4d6ab1180f 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/0c2dd4728/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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/0c2dd4728/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/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 0a83bc96e4..ee4e463d7c 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.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/0c2dd4728/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L641">runtime.ts:641</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/0c2dd4728/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L687">runtime.ts:687</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 b9ff9b54c8..6e7fb3d943 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/0c2dd4728/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L401">runtime.ts:401</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/0c2dd4728/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L394">runtime.ts:394</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/0c2dd4728/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<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/0c2dd4728/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<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/0c2dd4728/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L553">runtime.ts:553</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 0e0bbbef9f..75bbda1c01 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 0425429fc2..5f99839ae6 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/0c2dd4728/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L95">rpc_server.ts:95</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/0c2dd4728/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L84">rpc_server.ts:84</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/0c2dd4728/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L80">rpc_server.ts:80</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/0c2dd4728/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L83">rpc_server.ts:83</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/0c2dd4728/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L81">rpc_server.ts:81</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/0c2dd4728/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index 8001bb6785..d9c00ff22a 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index ad88bc2bf3..4de8b3f240 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index ac72edf34e..26348d03c4 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L730">runtime.ts:730</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/0c2dd4728/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index 10e8c84f1e..c828d208d7 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.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/0c2dd4728/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L730">runtime.ts:730</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/0c2dd4728/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 7222a1713f..82edb6226d 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 207429e52b..694c426870 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index e144645a28..47dbcd0d29 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L812">runtime.ts:812</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 3946819ef1..cc86790482 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L339">runtime.ts:339</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L337">runtime.ts:337</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L340">runtime.ts:340</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index d15b48329f..e0cdfa9fb2 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 0684c4d8d0..97639492c9 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 07f9c5c782..85069b5585 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -726,7 +726,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -765,7 +765,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -808,7 +808,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -838,7 +838,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -874,7 +874,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -922,7 +922,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -962,7 +962,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -998,7 +998,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Get<wbr>Type<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1037,7 +1037,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Index2<wbr>Key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_index<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, out_type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1076,7 +1076,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Key2<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1115,7 +1115,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1157,7 +1157,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1193,7 +1193,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1229,7 +1229,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1269,7 +1269,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1321,7 +1321,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1357,7 +1357,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1372,7 +1372,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L37">runtime.ts:37</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1387,7 +1387,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1402,7 +1402,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1417,7 +1417,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Base<span class="tsd-signature-symbol">:</span> <a href="classes/tvmobject.html" class="tsd-signature-type">TVMObject</a><span class="tsd-signature-symbol"> | </span><a href="classes/ndarray.html" class="tsd-signature-type">NDArray</a><span class="tsd-signature-symbol"> | </span><a href="classes/module.html" class="tsd-signature-type">Module</a><span class="tsd-signature-symbol"> | </span><a href="index.html#packedfunc" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L781">runtime.ts:781</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1435,7 +1435,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1457,7 +1457,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1489,7 +1489,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1518,7 +1518,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1555,7 +1555,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1586,7 +1586,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1608,7 +1608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1639,7 +1639,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1661,7 +1661,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1726,7 +1726,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1748,7 +1748,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L343">runtime.ts:343</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1757,7 +1757,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L344">runtime.ts:344</a></li>
</ul>
</aside>
</section>
@@ -1767,7 +1767,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L345">runtime.ts:345</a></li>
</ul>
</aside>
</section>
@@ -1777,7 +1777,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L346">runtime.ts:346</a></li>
</ul>
</aside>
</section>
@@ -1787,7 +1787,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L347">runtime.ts:347</a></li>
</ul>
</aside>
</section>
@@ -1798,7 +1798,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L272">runtime.ts:272</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1807,7 +1807,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L273">runtime.ts:273</a></li>
</ul>
</aside>
</section>
@@ -1817,7 +1817,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L277">runtime.ts:277</a></li>
</ul>
</aside>
</section>
@@ -1827,7 +1827,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L274">runtime.ts:274</a></li>
</ul>
</aside>
</section>
@@ -1837,7 +1837,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L275">runtime.ts:275</a></li>
</ul>
</aside>
</section>
@@ -1847,7 +1847,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L276">runtime.ts:276</a></li>
</ul>
</aside>
</section>
@@ -1858,7 +1858,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L280">runtime.ts:280</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1867,7 +1867,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L283">runtime.ts:283</a></li>
</ul>
</aside>
</section>
@@ -1877,7 +1877,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L281">runtime.ts:281</a></li>
</ul>
</aside>
</section>
@@ -1887,7 +1887,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L282">runtime.ts:282</a></li>
</ul>
</aside>
</section>
@@ -1897,7 +1897,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L286">runtime.ts:286</a></li>
</ul>
</aside>
</section>
@@ -1907,7 +1907,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L284">runtime.ts:284</a></li>
</ul>
</aside>
</section>
@@ -1917,7 +1917,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L285">runtime.ts:285</a></li>
</ul>
</aside>
</section>
@@ -1927,7 +1927,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/runtime.ts#L287">runtime.ts:287</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index e5749cc37f..1fad65a734 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index c70e16d118..6c640f1a1e 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 95837948ee..444d3229c1 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/0c2dd4728/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c7970ddd7/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 3ed41cefa1..d38b703dea 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index cea2966ebe..99ccba99fa 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:31.318</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:32.426</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,7 +354,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:31.312</p></td>
+<td><p>00:32.419</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 90fd697230..df9fdfb291 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -588,7 +588,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 33.65s!
+resnet18_v1 inference graph built in 35.66s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 7975ad6190..686c90d9bc 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -606,7 +606,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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 22.21s!
+yolov3-tiny inference graph built in 24.06s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 96bab47347..f3af4177a3 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:39.874</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:43.706</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:50.713</p></td>
+<td><p>00:52.781</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:49.160</p></td>
+<td><p>00:50.924</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 6d2cc6f2b8..640be24e3b 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.202</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.275</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.714</p></td>
+<td><p>00:02.778</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.488</p></td>
+<td><p>00:00.497</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 910fc8d60e..78bde0c332 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.434</p></td>
+<td><p>00:00.438</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.410</p></td>
+<td><p>00:00.407</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 0c6fc4dd58..ad735500b9 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -574,7 +574,7 @@ class Module:
<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: 94.659 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 97.542 ms
</pre></div>
</div>
</div>
@@ -646,7 +646,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.846 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.026 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index bf3aceb518..ba5df6929c 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -685,16 +685,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 1.26/1.26 result: MeasureResult(costs=(0.21357476339999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.654994010925293, timestamp=1679478656.1902423) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
-No: 2 GFLOPS: 9.00/9.00 result: MeasureResult(costs=(0.029832763999999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.107313871383667, timestamp=1679478656.9356382) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
-No: 3 GFLOPS: 12.96/12.96 result: MeasureResult(costs=(0.020711028,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7063040733337402, timestamp=1679478658.770175) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
-No: 4 GFLOPS: 9.74/12.96 result: MeasureResult(costs=(0.027567378400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6625292301177979, timestamp=1679478659.472333) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
-No: 5 GFLOPS: 11.52/12.96 result: MeasureResult(costs=(0.023292152400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6334025859832764, timestamp=1679478660.2453198) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
-No: 6 GFLOPS: 2.68/12.96 result: MeasureResult(costs=(0.100212551,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8593904972076416, timestamp=1679478663.3616052) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
-No: 7 GFLOPS: 10.36/12.96 result: MeasureResult(costs=(0.0259035974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6861972808837891, timestamp=1679478665.2850266) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
-No: 8 GFLOPS: 13.72/13.72 result: MeasureResult(costs=(0.0195708394,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5881080627441406, timestamp=1679478665.856312) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
-No: 9 GFLOPS: 3.25/13.72 result: MeasureResult(costs=(0.08261126040000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5338115692138672, timestamp=1679478667.5181794) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
-No: 10 GFLOPS: 11.74/13.72 result: MeasureResult(costs=(0.0228625504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.597022533416748, timestamp=1679478668.1488285) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
+No: 1 GFLOPS: 10.64/10.64 result: MeasureResult(costs=(0.0252406294,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6602799892425537, timestamp=1679478690.2342584) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+No: 2 GFLOPS: 9.91/10.64 result: MeasureResult(costs=(0.027085973800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.678652286529541, timestamp=1679478692.1526484) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+No: 3 GFLOPS: 2.07/10.64 result: MeasureResult(costs=(0.129673222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.315542697906494, timestamp=1679478695.7194266) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 4 GFLOPS: 1.31/10.64 result: MeasureResult(costs=(0.20482821499999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.505256175994873, timestamp=1679478699.2506433) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+No: 5 GFLOPS: 10.68/10.68 result: MeasureResult(costs=(0.0251386018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6770076751708984, timestamp=1679478700.0876095) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
+No: 6 GFLOPS: 2.52/10.68 result: MeasureResult(costs=(0.10664173699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9691181182861328, timestamp=1679478702.0530665) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
+No: 7 GFLOPS: 3.09/10.68 result: MeasureResult(costs=(0.086927122,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6492116451263428, timestamp=1679478704.928777) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+No: 8 GFLOPS: 10.23/10.68 result: MeasureResult(costs=(0.0262502968,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7269477844238281, timestamp=1679478705.6031437) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
+No: 9 GFLOPS: 1.34/10.68 result: MeasureResult(costs=(0.20104186799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.417808771133423, timestamp=1679478709.1393392) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
+No: 10 GFLOPS: 0.51/10.68 result: MeasureResult(costs=(0.5288554314,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.67240834236145, timestamp=1679478717.8649826) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index b3925cc3f8..b8346f2ab1 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -563,7 +563,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 514.2599545799976, 'median': 514.1435266999963, 'std': 1.985741545384889}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 512.1068799599993, 'median': 512.0930592999969, 'std': 2.9358509438286267}
</pre></div>
</div>
</div>
@@ -715,178 +715,177 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 11.30/ 13.53 GFLOPS | Progress: (4/20) | 11.24 s
-[Task 1/25] Current/Best: 22.84/ 22.84 GFLOPS | Progress: (8/20) | 16.08 s
-[Task 1/25] Current/Best: 12.38/ 22.84 GFLOPS | Progress: (12/20) | 19.86 s
-[Task 1/25] Current/Best: 6.42/ 22.84 GFLOPS | Progress: (16/20) | 24.03 s
-[Task 1/25] Current/Best: 11.17/ 22.84 GFLOPS | Progress: (20/20) | 29.40 s Done.
+[Task 1/25] Current/Best: 18.35/ 19.55 GFLOPS | Progress: (4/20) | 10.68 s
+[Task 1/25] Current/Best: 22.13/ 22.13 GFLOPS | Progress: (8/20) | 17.93 s
+[Task 1/25] Current/Best: 19.09/ 22.13 GFLOPS | Progress: (12/20) | 23.31 s
+[Task 1/25] Current/Best: 6.28/ 23.32 GFLOPS | Progress: (16/20) | 26.14 s
+[Task 1/25] Current/Best: 14.18/ 23.32 GFLOPS | Progress: (20/20) | 28.72 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 20.40/ 20.82 GFLOPS | Progress: (4/20) | 4.36 s
-[Task 2/25] Current/Best: 20.43/ 20.82 GFLOPS | Progress: (8/20) | 5.71 s
-[Task 2/25] Current/Best: 8.75/ 20.82 GFLOPS | Progress: (12/20) | 7.34 s
-[Task 2/25] Current/Best: 15.94/ 20.82 GFLOPS | Progress: (16/20) | 8.81 s
-[Task 2/25] Current/Best: 17.17/ 20.82 GFLOPS | Progress: (20/20) | 10.33 s Done.
+[Task 2/25] Current/Best: 12.07/ 15.55 GFLOPS | Progress: (4/20) | 4.46 s
+[Task 2/25] Current/Best: 18.97/ 18.97 GFLOPS | Progress: (8/20) | 6.42 s
+[Task 2/25] Current/Best: 16.89/ 20.73 GFLOPS | Progress: (12/20) | 7.85 s
+[Task 2/25] Current/Best: 8.28/ 20.73 GFLOPS | Progress: (16/20) | 10.79 s
+[Task 2/25] Current/Best: 5.78/ 20.73 GFLOPS | Progress: (20/20) | 12.40 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 24.02/ 24.02 GFLOPS | Progress: (4/20) | 5.96 s
-[Task 3/25] Current/Best: 17.92/ 24.02 GFLOPS | Progress: (8/20) | 8.10 s
-[Task 3/25] Current/Best: 16.30/ 24.02 GFLOPS | Progress: (12/20) | 10.43 s
-[Task 3/25] Current/Best: 20.90/ 24.02 GFLOPS | Progress: (16/20) | 13.07 s
-[Task 3/25] Current/Best: 8.44/ 24.02 GFLOPS | Progress: (20/20) | 15.69 s Done.
+[Task 3/25] Current/Best: 17.98/ 18.16 GFLOPS | Progress: (4/20) | 6.25 s
+[Task 3/25] Current/Best: 12.72/ 20.96 GFLOPS | Progress: (8/20) | 8.61 s
+[Task 3/25] Current/Best: 7.75/ 20.96 GFLOPS | Progress: (12/20) | 11.89 s
+[Task 3/25] Current/Best: 18.43/ 20.96 GFLOPS | Progress: (16/20) | 14.35 s
+[Task 3/25] Current/Best: 19.21/ 20.96 GFLOPS | Progress: (20/20) | 17.67 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 3.94/ 12.38 GFLOPS | Progress: (4/20) | 5.03 s
-[Task 4/25] Current/Best: 12.22/ 16.94 GFLOPS | Progress: (8/20) | 7.09 s
-[Task 4/25] Current/Best: 21.42/ 21.42 GFLOPS | Progress: (12/20) | 12.00 s
-[Task 4/25] Current/Best: 5.05/ 21.42 GFLOPS | Progress: (16/20) | 14.37 s
-[Task 4/25] Current/Best: 14.85/ 21.93 GFLOPS | Progress: (20/20) | 16.06 s Done.
+[Task 4/25] Current/Best: 11.63/ 19.56 GFLOPS | Progress: (4/20) | 5.72 s
+[Task 4/25] Current/Best: 11.55/ 19.56 GFLOPS | Progress: (8/20) | 10.61 s
+[Task 4/25] Current/Best: 4.93/ 19.56 GFLOPS | Progress: (12/20) | 15.52 s
+[Task 4/25] Current/Best: 6.48/ 19.56 GFLOPS | Progress: (16/20) | 17.97 s
+[Task 4/25] Current/Best: 5.62/ 19.56 GFLOPS | Progress: (20/20) | 20.40 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 4.22/ 14.28 GFLOPS | Progress: (4/20) | 5.38 s
-[Task 5/25] Current/Best: 17.60/ 17.60 GFLOPS | Progress: (8/20) | 8.07 s
-[Task 5/25] Current/Best: 6.34/ 19.80 GFLOPS | Progress: (12/20) | 10.45 s
-[Task 5/25] Current/Best: 15.26/ 20.16 GFLOPS | Progress: (16/20) | 12.08 s
-[Task 5/25] Current/Best: 2.78/ 20.16 GFLOPS | Progress: (20/20) | 14.51 s Done.
+[Task 5/25] Current/Best: 10.02/ 15.96 GFLOPS | Progress: (4/20) | 5.48 s
+[Task 5/25] Current/Best: 11.41/ 15.96 GFLOPS | Progress: (8/20) | 8.16 s
+[Task 5/25] Current/Best: 12.78/ 15.96 GFLOPS | Progress: (12/20) | 11.03 s
+[Task 5/25] Current/Best: 13.05/ 17.99 GFLOPS | Progress: (16/20) | 13.08 s
+[Task 5/25] Current/Best: 14.80/ 17.99 GFLOPS | Progress: (20/20) | 15.29 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 10.26/ 17.45 GFLOPS | Progress: (4/20) | 5.20 s
-[Task 6/25] Current/Best: 12.40/ 17.45 GFLOPS | Progress: (8/20) | 7.45 s
-[Task 6/25] Current/Best: 3.01/ 17.45 GFLOPS | Progress: (12/20) | 12.20 s
-[Task 6/25] Current/Best: 15.27/ 17.45 GFLOPS | Progress: (16/20) | 15.45 s
-[Task 6/25] Current/Best: 15.92/ 17.45 GFLOPS | Progress: (20/20) | 19.53 s Done.
+[Task 6/25] Current/Best: 12.84/ 19.49 GFLOPS | Progress: (4/20) | 5.17 s
+[Task 6/25] Current/Best: 12.95/ 19.49 GFLOPS | Progress: (8/20) | 7.52 s
+[Task 6/25] Current/Best: 6.08/ 19.49 GFLOPS | Progress: (12/20) | 10.92 s
+[Task 6/25] Current/Best: 13.64/ 19.49 GFLOPS | Progress: (16/20) | 13.91 s
+[Task 6/25] Current/Best: 14.31/ 19.49 GFLOPS | Progress: (20/20) | 17.29 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 19.35/ 19.35 GFLOPS | Progress: (4/20) | 5.00 s
-[Task 7/25] Current/Best: 5.90/ 19.35 GFLOPS | Progress: (8/20) | 8.25 s
-[Task 7/25] Current/Best: 22.12/ 22.12 GFLOPS | Progress: (12/20) | 10.16 s
-[Task 7/25] Current/Best: 8.68/ 22.12 GFLOPS | Progress: (16/20) | 12.78 s
-[Task 7/25] Current/Best: 3.13/ 22.12 GFLOPS | Progress: (20/20) | 15.98 s Done.
+[Task 7/25] Current/Best: 3.06/ 18.50 GFLOPS | Progress: (4/20) | 5.29 s
+[Task 7/25] Current/Best: 5.76/ 18.50 GFLOPS | Progress: (8/20) | 8.06 s
+[Task 7/25] Current/Best: 9.60/ 18.50 GFLOPS | Progress: (12/20) | 11.09 s
+[Task 7/25] Current/Best: 18.01/ 18.50 GFLOPS | Progress: (16/20) | 13.33 s
+[Task 7/25] Current/Best: 12.58/ 18.50 GFLOPS | Progress: (20/20) | 16.03 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.10/ 12.04 GFLOPS | Progress: (4/20) | 8.38 s
-[Task 8/25] Current/Best: 2.44/ 21.12 GFLOPS | Progress: (8/20) | 11.53 s
-[Task 8/25] Current/Best: 22.06/ 22.06 GFLOPS | Progress: (12/20) | 14.12 s
-[Task 8/25] Current/Best: 9.76/ 22.06 GFLOPS | Progress: (16/20) | 20.31 s
-[Task 8/25] Current/Best: 2.89/ 22.06 GFLOPS | Progress: (20/20) | 23.62 s Done.
+[Task 8/25] Current/Best: 4.98/ 16.88 GFLOPS | Progress: (4/20) | 5.09 s
+[Task 8/25] Current/Best: 10.58/ 16.88 GFLOPS | Progress: (8/20) | 8.04 s
+[Task 8/25] Current/Best: 2.93/ 16.88 GFLOPS | Progress: (12/20) | 15.22 s
+[Task 8/25] Current/Best: 17.79/ 17.79 GFLOPS | Progress: (16/20) | 18.34 s
+[Task 8/25] Current/Best: 10.44/ 17.79 GFLOPS | Progress: (20/20) | 21.69 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 15.58/ 15.58 GFLOPS | Progress: (4/20) | 5.14 s
-[Task 9/25] Current/Best: 11.42/ 17.02 GFLOPS | Progress: (8/20) | 8.55 s
-[Task 9/25] Current/Best: 15.90/ 17.02 GFLOPS | Progress: (12/20) | 10.71 s
-[Task 9/25] Current/Best: 10.89/ 19.04 GFLOPS | Progress: (16/20) | 16.06 s
-[Task 9/25] Current/Best: 14.22/ 19.04 GFLOPS | Progress: (20/20) | 21.81 s Done.
+[Task 9/25] Current/Best: 8.84/ 17.45 GFLOPS | Progress: (4/20) | 7.46 s
+[Task 9/25] Current/Best: 4.82/ 17.45 GFLOPS | Progress: (8/20) | 15.45 s
+[Task 9/25] Current/Best: 6.03/ 17.45 GFLOPS | Progress: (12/20) | 23.85 s
+[Task 9/25] Current/Best: 10.20/ 17.45 GFLOPS | Progress: (16/20) | 27.59 s
+[Task 9/25] Current/Best: 19.69/ 19.69 GFLOPS | Progress: (20/20) | 29.33 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.02/ 18.02 GFLOPS | Progress: (4/20) | 4.83 s
-[Task 10/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (8/20) | 7.81 s
-[Task 10/25] Current/Best: 5.74/ 18.15 GFLOPS | Progress: (12/20) | 9.72 s
-[Task 10/25] Current/Best: 12.55/ 20.01 GFLOPS | Progress: (16/20) | 11.87 s
-[Task 10/25] Current/Best: 8.17/ 20.01 GFLOPS | Progress: (20/20) | 15.26 s Done.
+[Task 10/25] Current/Best: 15.08/ 16.05 GFLOPS | Progress: (4/20) | 4.36 s
+[Task 10/25] Current/Best: 10.87/ 17.31 GFLOPS | Progress: (8/20) | 6.08 s
+[Task 10/25] Current/Best: 14.95/ 18.78 GFLOPS | Progress: (12/20) | 8.12 s
+[Task 10/25] Current/Best: 12.79/ 22.75 GFLOPS | Progress: (16/20) | 10.40 s
+[Task 10/25] Current/Best: 4.81/ 22.75 GFLOPS | Progress: (20/20) | 12.10 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (4/20) | 5.33 s
-[Task 11/25] Current/Best: 19.07/ 21.41 GFLOPS | Progress: (8/20) | 7.33 s
-[Task 11/25] Current/Best: 6.89/ 21.41 GFLOPS | Progress: (12/20) | 11.69 s
-[Task 11/25] Current/Best: 18.31/ 21.41 GFLOPS | Progress: (16/20) | 13.87 s
-[Task 11/25] Current/Best: 19.33/ 21.41 GFLOPS | Progress: (20/20) | 17.36 s Done.
+[Task 11/25] Current/Best: 6.20/ 14.92 GFLOPS | Progress: (4/20) | 5.64 s
+[Task 11/25] Current/Best: 12.16/ 22.25 GFLOPS | Progress: (8/20) | 8.31 s
+[Task 11/25] Current/Best: 3.10/ 22.25 GFLOPS | Progress: (12/20) | 12.12 s
+[Task 11/25] Current/Best: 20.40/ 23.24 GFLOPS | Progress: (16/20) | 14.57 s
+[Task 11/25] Current/Best: 16.05/ 23.24 GFLOPS | Progress: (20/20) | 16.71 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 11.61/ 15.76 GFLOPS | Progress: (4/20) | 5.07 s
-[Task 12/25] Current/Best: 11.44/ 15.76 GFLOPS | Progress: (8/20) | 9.12 s
-[Task 12/25] Current/Best: 14.47/ 15.77 GFLOPS | Progress: (12/20) | 15.72 s
-[Task 12/25] Current/Best: 12.68/ 15.77 GFLOPS | Progress: (16/20) | 19.42 s
-[Task 12/25] Current/Best: 18.33/ 18.33 GFLOPS | Progress: (20/20) | 21.69 s Done.
+[Task 12/25] Current/Best: 10.35/ 13.70 GFLOPS | Progress: (4/20) | 7.59 s
+[Task 12/25] Current/Best: 14.62/ 20.51 GFLOPS | Progress: (8/20) | 9.75 s
+[Task 12/25] Current/Best: 7.79/ 20.51 GFLOPS | Progress: (12/20) | 13.58 s
+[Task 12/25] Current/Best: 10.16/ 20.51 GFLOPS | Progress: (16/20) | 18.73 s
+[Task 12/25] Current/Best: 11.29/ 20.51 GFLOPS | Progress: (20/20) | 22.19 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 5.73/ 11.65 GFLOPS | Progress: (4/20) | 6.51 s
-[Task 13/25] Current/Best: 15.23/ 19.12 GFLOPS | Progress: (8/20) | 9.27 s
-[Task 13/25] Current/Best: 9.70/ 19.12 GFLOPS | Progress: (12/20) | 12.50 s
-[Task 13/25] Current/Best: 15.28/ 23.20 GFLOPS | Progress: (16/20) | 14.92 s
-[Task 13/25] Current/Best: 12.84/ 23.20 GFLOPS | Progress: (20/20) | 17.92 s Done.
+[Task 13/25] Current/Best: 4.58/ 16.86 GFLOPS | Progress: (4/20) | 6.06 s
+[Task 13/25] Current/Best: 11.62/ 16.86 GFLOPS | Progress: (8/20) | 10.08 s
+[Task 13/25] Current/Best: 16.46/ 16.86 GFLOPS | Progress: (12/20) | 13.93 s
+[Task 13/25] Current/Best: 7.93/ 20.34 GFLOPS | Progress: (16/20) | 17.35 s
+[Task 13/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (20/20) | 20.48 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 9.60/ 12.95 GFLOPS | Progress: (4/20) | 5.20 s
-[Task 14/25] Current/Best: 9.89/ 15.08 GFLOPS | Progress: (8/20) | 9.00 s
-[Task 14/25] Current/Best: 13.46/ 18.57 GFLOPS | Progress: (12/20) | 11.24 s
-[Task 14/25] Current/Best: 16.27/ 18.57 GFLOPS | Progress: (16/20) | 13.34 s
-[Task 14/25] Current/Best: 16.22/ 18.57 GFLOPS | Progress: (20/20) | 17.30 s Done.
-
+[Task 14/25] Current/Best: 13.78/ 13.78 GFLOPS | Progress: (4/20) | 4.60 s
+[Task 14/25] Current/Best: 12.64/ 13.78 GFLOPS | Progress: (8/20) | 9.21 s
+[Task 14/25] Current/Best: 8.19/ 17.70 GFLOPS | Progress: (12/20) | 11.50 s
+[Task 14/25] Current/Best: 9.19/ 17.70 GFLOPS | Progress: (16/20) | 15.46 s
+[Task 14/25] Current/Best: 21.44/ 21.44 GFLOPS | Progress: (20/20) | 20.16 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 18.32/ 18.86 GFLOPS | Progress: (4/20) | 4.29 s
-[Task 15/25] Current/Best: 6.03/ 19.97 GFLOPS | Progress: (8/20) | 7.03 s
-[Task 15/25] Current/Best: 15.84/ 23.63 GFLOPS | Progress: (12/20) | 9.96 s
-[Task 15/25] Current/Best: 8.32/ 23.63 GFLOPS | Progress: (16/20) | 17.26 s
-[Task 15/25] Current/Best: 12.81/ 23.63 GFLOPS | Progress: (20/20) | 19.37 s
+[Task 15/25] Current/Best: 14.26/ 19.72 GFLOPS | Progress: (4/20) | 5.44 s
+[Task 15/25] Current/Best: 23.12/ 23.12 GFLOPS | Progress: (8/20) | 8.36 s
+[Task 15/25] Current/Best: 19.92/ 23.12 GFLOPS | Progress: (12/20) | 11.75 s
+[Task 15/25] Current/Best: 10.15/ 23.12 GFLOPS | Progress: (16/20) | 13.64 s
+[Task 15/25] Current/Best: 13.16/ 23.12 GFLOPS | Progress: (20/20) | 15.88 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 14.90/ 18.08 GFLOPS | Progress: (4/20) | 6.13 s
-[Task 16/25] Current/Best: 15.74/ 18.08 GFLOPS | Progress: (8/20) | 8.00 s
-[Task 16/25] Current/Best: 17.73/ 18.16 GFLOPS | Progress: (12/20) | 10.32 s
-[Task 16/25] Current/Best: 9.73/ 18.16 GFLOPS | Progress: (16/20) | 13.47 s
-[Task 16/25] Current/Best: 13.17/ 18.16 GFLOPS | Progress: (20/20) | 16.56 s Done.
+[Task 16/25] Current/Best: 5.82/ 14.68 GFLOPS | Progress: (4/20) | 4.68 s
+[Task 16/25] Current/Best: 13.21/ 14.68 GFLOPS | Progress: (8/20) | 8.00 s
+[Task 16/25] Current/Best: 18.55/ 18.55 GFLOPS | Progress: (12/20) | 9.78 s
+[Task 16/25] Current/Best: 14.12/ 18.55 GFLOPS | Progress: (16/20) | 12.52 s
+[Task 16/25] Current/Best: 11.26/ 18.55 GFLOPS | Progress: (20/20) | 16.14 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 17.35/ 18.82 GFLOPS | Progress: (4/20) | 5.35 s
-[Task 17/25] Current/Best: 15.82/ 18.82 GFLOPS | Progress: (8/20) | 8.54 s
-[Task 17/25] Current/Best: 17.15/ 20.89 GFLOPS | Progress: (12/20) | 10.46 s
-[Task 17/25] Current/Best: 5.37/ 20.89 GFLOPS | Progress: (16/20) | 13.22 s
-[Task 17/25] Current/Best: 23.70/ 23.70 GFLOPS | Progress: (20/20) | 16.04 s Done.
+[Task 17/25] Current/Best: 12.28/ 20.42 GFLOPS | Progress: (4/20) | 5.03 s
+[Task 17/25] Current/Best: 16.62/ 20.42 GFLOPS | Progress: (8/20) | 7.34 s
+[Task 17/25] Current/Best: 12.46/ 20.42 GFLOPS | Progress: (12/20) | 10.34 s
+[Task 17/25] Current/Best: 7.64/ 20.42 GFLOPS | Progress: (16/20) | 13.17 s
+[Task 17/25] Current/Best: 20.36/ 20.42 GFLOPS | Progress: (20/20) | 16.35 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.94/ 11.94 GFLOPS | Progress: (4/20) | 6.98 s
-[Task 18/25] Current/Best: 19.96/ 19.96 GFLOPS | Progress: (8/20) | 9.32 s
-[Task 18/25] Current/Best: 10.06/ 19.96 GFLOPS | Progress: (12/20) | 13.46 s
-[Task 18/25] Current/Best: 6.61/ 19.96 GFLOPS | Progress: (16/20) | 15.84 s
-[Task 18/25] Current/Best: 13.72/ 19.96 GFLOPS | Progress: (20/20) | 18.95 s Done.
+[Task 18/25] Current/Best: 17.86/ 19.00 GFLOPS | Progress: (4/20) | 4.53 s
+[Task 18/25] Current/Best: 18.33/ 21.06 GFLOPS | Progress: (8/20) | 8.01 s
+[Task 18/25] Current/Best: 12.09/ 21.06 GFLOPS | Progress: (12/20) | 10.91 s
+[Task 18/25] Current/Best: 14.74/ 21.06 GFLOPS | Progress: (16/20) | 13.30 s
+[Task 18/25] Current/Best: 18.47/ 21.06 GFLOPS | Progress: (20/20) | 15.44 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 21.31/ 21.31 GFLOPS | Progress: (4/20) | 8.62 s
-[Task 19/25] Current/Best: 9.20/ 21.31 GFLOPS | Progress: (8/20) | 12.61 s
-[Task 19/25] Current/Best: 17.91/ 21.31 GFLOPS | Progress: (12/20) | 14.71 s
-[Task 19/25] Current/Best: 12.91/ 21.31 GFLOPS | Progress: (16/20) | 18.72 s
-[Task 19/25] Current/Best: 11.91/ 21.31 GFLOPS | Progress: (20/20) | 23.72 s Done.
+[Task 19/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (4/20) | 5.75 s
+[Task 19/25] Current/Best: 11.05/ 19.96 GFLOPS | Progress: (8/20) | 8.79 s
+[Task 19/25] Current/Best: 18.73/ 19.96 GFLOPS | Progress: (12/20) | 11.48 s
+[Task 19/25] Current/Best: 10.46/ 21.35 GFLOPS | Progress: (16/20) | 16.78 s
+[Task 19/25] Current/Best: 8.87/ 21.35 GFLOPS | Progress: (20/20) | 21.20 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 2.69/ 20.31 GFLOPS | Progress: (4/20) | 5.56 s
-[Task 20/25] Current/Best: 20.17/ 20.31 GFLOPS | Progress: (8/20) | 7.64 s
-[Task 20/25] Current/Best: 12.80/ 20.31 GFLOPS | Progress: (12/20) | 10.04 s
-[Task 20/25] Current/Best: 7.52/ 20.31 GFLOPS | Progress: (16/20) | 13.94 s
-[Task 20/25] Current/Best: 9.59/ 20.31 GFLOPS | Progress: (20/20) | 17.00 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 2.72/ 15.55 GFLOPS | Progress: (4/20) | 6.05 s
-[Task 21/25] Current/Best: 14.11/ 15.55 GFLOPS | Progress: (8/20) | 8.01 s
-[Task 21/25] Current/Best: 15.46/ 18.54 GFLOPS | Progress: (12/20) | 10.92 s Done.
- Done.
-
-[Task 21/25] Current/Best: 19.94/ 19.94 GFLOPS | Progress: (16/20) | 13.35 s
-[Task 21/25] Current/Best: 15.04/ 19.94 GFLOPS | Progress: (20/20) | 16.29 s
+[Task 20/25] Current/Best: 12.95/ 12.95 GFLOPS | Progress: (4/20) | 5.51 s
+[Task 20/25] Current/Best: 11.51/ 17.19 GFLOPS | Progress: (8/20) | 11.85 s
+[Task 20/25] Current/Best: 14.40/ 17.19 GFLOPS | Progress: (12/20) | 13.28 s
+[Task 20/25] Current/Best: 14.41/ 18.21 GFLOPS | Progress: (16/20) | 17.44 s
+[Task 20/25] Current/Best: 9.54/ 18.21 GFLOPS | Progress: (20/20) | 19.63 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 21/25] Current/Best: 16.47/ 19.56 GFLOPS | Progress: (4/20) | 5.19 s
+[Task 21/25] Current/Best: 14.75/ 19.56 GFLOPS | Progress: (8/20) | 8.17 s
+[Task 21/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (12/20) | 10.02 s
+[Task 21/25] Current/Best: 9.65/ 20.06 GFLOPS | Progress: (16/20) | 12.80 s
+[Task 21/25] Current/Best: 10.12/ 20.06 GFLOPS | Progress: (20/20) | 16.02 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 8.64/ 20.04 GFLOPS | Progress: (4/20) | 4.86 s
-[Task 22/25] Current/Best: 7.75/ 20.04 GFLOPS | Progress: (8/20) | 7.24 s
-[Task 22/25] Current/Best: 12.32/ 20.04 GFLOPS | Progress: (12/20) | 9.11 s
-[Task 22/25] Current/Best: 7.25/ 20.04 GFLOPS | Progress: (16/20) | 10.80 s
-[Task 22/25] Current/Best: 5.26/ 20.04 GFLOPS | Progress: (20/20) | 14.47 s Done.
+[Task 22/25] Current/Best: 7.98/ 19.96 GFLOPS | Progress: (4/20) | 4.70 s
+[Task 22/25] Current/Best: 4.92/ 19.96 GFLOPS | Progress: (8/20) | 8.05 s
+[Task 22/25] Current/Best: 16.80/ 19.96 GFLOPS | Progress: (12/20) | 9.64 s
+[Task 22/25] Current/Best: 19.03/ 19.96 GFLOPS | Progress: (16/20) | 11.57 s
+[Task 22/25] Current/Best: 7.67/ 19.96 GFLOPS | Progress: (20/20) | 15.04 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 10.42/ 10.42 GFLOPS | Progress: (4/20) | 7.69 s
-[Task 23/25] Current/Best: 23.74/ 23.74 GFLOPS | Progress: (8/20) | 11.67 s
-[Task 23/25] Current/Best: 10.24/ 23.74 GFLOPS | Progress: (12/20) | 14.75 s
-[Task 23/25] Current/Best: 11.89/ 23.74 GFLOPS | Progress: (16/20) | 18.06 s
-[Task 23/25] Current/Best: 12.09/ 23.74 GFLOPS | Progress: (20/20) | 21.18 s Done.
+[Task 23/25] Current/Best: 19.78/ 19.90 GFLOPS | Progress: (4/20) | 4.99 s
+[Task 23/25] Current/Best: 10.45/ 19.90 GFLOPS | Progress: (8/20) | 9.37 s
+[Task 23/25] Current/Best: 1.55/ 19.90 GFLOPS | Progress: (12/20) | 14.80 s
+[Task 23/25] Current/Best: 14.69/ 20.54 GFLOPS | Progress: (16/20) | 17.00 s
+[Task 23/25] Current/Best: 12.43/ 20.54 GFLOPS | Progress: (20/20) | 19.74 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (4/20) | 12.84 s
-[Task 24/25] Current/Best: 1.09/ 3.81 GFLOPS | Progress: (8/20) | 25.51 s
-[Task 24/25] Current/Best: 3.42/ 4.03 GFLOPS | Progress: (12/20) | 38.12 s
-[Task 24/25] Current/Best: 1.45/ 4.03 GFLOPS | Progress: (16/20) | 50.76 s
-[Task 24/25] Current/Best: 1.55/ 4.03 GFLOPS | Progress: (20/20) | 61.76 s
+[Task 24/25] Current/Best: 0.50/ 4.88 GFLOPS | Progress: (4/20) | 13.78 s
+[Task 24/25] Current/Best: 3.41/ 4.88 GFLOPS | Progress: (8/20) | 26.24 s
+[Task 24/25] Current/Best: 6.63/ 10.91 GFLOPS | Progress: (12/20) | 28.83 s
+[Task 24/25] Current/Best: 7.18/ 10.91 GFLOPS | Progress: (16/20) | 31.05 s
+[Task 24/25] Current/Best: 2.82/ 10.91 GFLOPS | Progress: (20/20) | 42.01 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-[Task 25/25] Current/Best: 8.88/ 8.88 GFLOPS | Progress: (4/20) | 14.95 s
-[Task 25/25] Current/Best: 1.53/ 8.88 GFLOPS | Progress: (8/20) | 27.53 s
-[Task 25/25] Current/Best: 1.55/ 8.88 GFLOPS | Progress: (12/20) | 30.68 s
-[Task 25/25] Current/Best: 9.36/ 9.36 GFLOPS | Progress: (16/20) | 41.34 s
-[Task 25/25] Current/Best: 1.55/ 9.36 GFLOPS | Progress: (20/20) | 52.30 s
+[Task 25/25] Current/Best: 8.78/ 8.78 GFLOPS | Progress: (4/20) | 14.88 s
+[Task 25/25] Current/Best: 4.18/ 8.78 GFLOPS | Progress: (8/20) | 26.79 s
+[Task 25/25] Current/Best: 2.98/ 8.78 GFLOPS | Progress: (12/20) | 37.78 s
+[Task 25/25] Current/Best: 1.42/ 8.78 GFLOPS | Progress: (16/20) | 46.94 s
+[Task 25/25] Current/Best: 1.54/ 8.78 GFLOPS | Progress: (20/20) | 57.89 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -947,8 +946,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621102
-class='n02123159 tiger cat' with probability=0.356379
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
+class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -985,8 +984,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 402.02047891000575, 'median': 401.28876339999806, 'std': 3.301314593790155}
-unoptimized: {'mean': 514.2599545799976, 'median': 514.1435266999963, 'std': 1.985741545384889}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 427.58227047000446, 'median': 427.03722730001346, 'std': 2.9315160685878006}
+unoptimized: {'mean': 512.1068799599993, 'median': 512.0930592999969, 'std': 2.9358509438286267}
</pre></div>
</div>
</div>
@@ -1000,7 +999,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 41.810 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 34.455 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index c547989d80..b6bba1b5d3 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -543,7 +543,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.374e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.242e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 81eac9341d..bf39286440 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -513,7 +513,7 @@ class Module:
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x25288c80)), stage(b, placeholder(b, 0xac1bec0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x228231e0)), stage(b, placeholder(b, 0x83aa7f0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 01978bdb35..b09b8a9c06 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>16:19.279</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>16:13.386</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>12:41.810</p></td>
+<td><p>12:34.455</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:34.846</p></td>
+<td><p>01:24.026</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.262</p></td>
+<td><p>01:01.178</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:36.515</p></td>
+<td><p>00:36.611</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:22.444</p></td>
+<td><p>00:34.658</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.372</p></td>
+<td><p>00:01.454</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.855</p></td>
+<td><p>00:00.842</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.176</p></td>
+<td><p>00:00.163</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index d2e467b1a3..cd4f0719c8 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -554,7 +554,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000007
</pre></div>
</div>
@@ -610,7 +610,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000006
</pre></div>
</div>
</div>
@@ -686,10 +686,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.207910000237461e-06 1.0
- naive 6.725399999999999e-06 0.8193803294389714
-parallel 7.9832e-06 0.9726227504649831
- vector 2.45207e-05 2.9874474743619994
+ numpy 7.482219998564687e-06 1.0
+ naive 6.641e-06 0.8875708013495917
+parallel 6.042800000000001e-06 0.8076212676397099
+ vector 2.4598000000000004e-05 3.2875269645531184
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1005,7 +1005,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017925
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018556
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1046,7 +1046,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.441236
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.427779
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1110,7 +1110,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.300444
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.295800
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1159,7 +1159,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.334547
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.336362
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1208,7 +1208,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.114626
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.113505
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1278,7 +1278,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108260
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.107278
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1344,7 +1344,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110493
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110022
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1401,7 +1401,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146488
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145588
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1454,13 +1454,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4412356548999994 1.0
- blocking 0.3004442279 0.08730707746567586
- vectorization 0.33454658309999996 0.09721699315292075
-loop permutation 0.1146258668 0.033309508064867176
- array packing 0.1082601003 0.03145965901691379
- block caching 0.11049327 0.03210860315325045
- parallelization 0.1464880269 0.042568438081656716
+ none 3.4277789188 1.0
+ blocking 0.2957996004 0.08629483038642229
+ vectorization 0.33636178299999997 0.09812820224641378
+loop permutation 0.11350530429999998 0.03311336786554952
+ array packing 0.1072782304 0.03129671806183931
+ block caching 0.110022023 0.032097175928287876
+ parallelization 0.1455881197 0.04247301916162306
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1492,7 +1492,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.262 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.178 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>