You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/08/25 12:35:36 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@40bdea8d7ae1109e33ac64265b4819bb8ebef8b3)
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 91abe598e deploying docs (apache/tvm@40bdea8d7ae1109e33ac64265b4819bb8ebef8b3)
91abe598e is described below
commit 91abe598e12140dee6ab39093fae7be16c87656b
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Aug 25 12:35:30 2022 +0000
deploying docs (apache/tvm@40bdea8d7ae1109e33ac64265b4819bb8ebef8b3)
---
.../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 | 5 -
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 564 ++++++---------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 271 +++-------
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 7 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/genindex.html | 14 +-
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 | 13 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 1 -
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 47 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 563 ++++++--------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 271 +++-------
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/objects.inv | Bin 23338 -> 23374 bytes
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/tir.html | 275 +++++++---
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 3 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +++++-----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 28 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
124 files changed, 1484 insertions(+), 2105 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index c21bb1f8a..8438ff39d 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.447 seconds)
+ **Total running time of the script:** ( 1 minutes 0.536 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 d4bda7da1..51bd51746 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa9609e41-0c3b-4baf-8ae1-e251c31d7545 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7ae95aaa-5e7d-4c63-8e08-47bfe20c581d 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 75aa49cd7..6c5cb9d54 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 43.3MB/s]
25%|##5 | 10.5M/41.5M [00:00<00:00, 39.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 31.6MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 27.8MB/s]
61%|###### | 25.1M/41.5M [00:00<00:00, 27.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 36.7MB/s]
90%|########9 | 37.2M/41.5M [00:01<00:00, 37.8MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 36.5MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 47.7MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 34.5MB/s]
54%|#####4 | 22.5M/41.5M [00:00<00:00, 48.6MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 55.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 59.2MB/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 c6201d06d..f2107eb50 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
41%|#### | 18.1M/44.7M [00:00<00:00, 190MB/s]
86%|########6 | 38.5M/44.7M [00:00<00:00, 204MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 211MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
32%|###1 | 14.2M/44.7M [00:00<00:00, 149MB/s]
83%|########3 | 37.2M/44.7M [00:00<00:00, 203MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 204MB/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 585729cc1..c3eaf267e 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -421,11 +421,6 @@ Run the corresponding model on tensorflow
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 5.397 seconds)
-
-
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
.. only:: html
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 ef84ec5fd..e2efc2e6b 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:09.102** total execution time for **how_to_compile_models** files:
+**04:51.864** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:05.447 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:00.536 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.397 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 00:59.356 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.937 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:37.734 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.200 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.212 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.751 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.624 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.124 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.208 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.269 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.019 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.705 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.564 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.764 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.341 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.506 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.269 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 41f5837c1..81f627f9a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4429 16.0607 20.0315 15.9354 1.1987
+ 16.9002 17.1537 17.4191 16.2652 0.5079
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 29e9fec2d..36760ff6e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 3.81M/170M [00:00<00:04, 39.1MB/s]
4%|4 | 7.55M/170M [00:00<00:04, 38.6MB/s]
7%|6 | 11.2M/170M [00:00<00:04, 37.0MB/s]
9%|8 | 15.0M/170M [00:00<00:04, 37.9MB/s]
11%|#1 | 19.2M/170M [00:00<00:03, 39.8MB/s]
15%|#4 | 24.9M/170M [00:00<00:03, 46.5MB/s]
17%|#7 | 29.4M/170M [00:00<00:03, 40.1MB/s]
21%|## | 35.1M/170M [00:00<00:03, 45.5MB/s]
24%|##4 | 41.1M/170M [00:00<00:02, 50.4MB/s]
27%|##7 | 46.1M/170M [00:01<00:02, 43.4MB/s]
30%|##9 | 50.5M/170M [00:01<00:02, 44.2MB/s]
32%|###2 | 54.9M/170M [00:01<00:02, 41.8MB/s]
35%|###4 | 59.0M/170M [00:01<00:02, 41.6MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 44.5MB/s]
40%|#### | 68.8M/170M [00:01<00:02, 46.0MB/s]
43%|####3 | 73.2M/170M [00:01<00:03, 33.6MB/s]
46%|####5 | 77.9M/170M [00:01<00:02, 37.2MB/
s]
49%|####8 | 83.1M/170M [00:02<00:02, 41.2MB/s]
51%|#####1 | 87.4M/170M [00:02<00:02, 36.7MB/s]
54%|#####3 | 91.2M/170M [00:02<00:02, 35.1MB/s]
56%|#####6 | 95.2M/170M [00:02<00:02, 36.6MB/s]
60%|#####9 | 101M/170M [00:02<00:01, 43.8MB/s]
63%|######2 | 107M/170M [00:02<00:01, 46.9MB/s]
66%|######5 | 112M/170M [00:02<00:01, 47.8MB/s]
70%|######9 | 119M/170M [00:02<00:00, 55.2MB/s]
73%|#######3 | 124M/170M [00:03<00:01, 39.9MB/s]
76%|#######5 | 129M/170M [00:03<00:01, 38.7MB/s]
78%|#######8 | 133M/170M [00:03<00:00, 40.3MB/s]
81%|######## | 137M/170M [00:03<00:00, 38.4MB/s]
83%|########3 | 141M/170M [00:03<00:00, 39.7MB/s]
86%|########5 | 145M/170M [00:03<00:00, 38.0MB/s]
88%|########7 | 149M/170M [00:03<00:00, 38.7MB/s]
91%|######### | 154M/170M [00:03<00:00, 40.6MB/s]
93%|#########3| 159M/170M [00:04<00:00, 42.7MB/s]
97%|#########6| 164M/170M [00:04<00:00, 46.3MB/s]
100%|#########9| 169M/170M [00:04<00:00, 49.0MB/s]
100%|##########| 170M/170M [00:04<00:00, 41.9MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.90M/170M [00:00<00:03, 50.6MB/s]
6%|6 | 10.6M/170M [00:00<00:02, 55.7MB/s]
22%|##2 | 38.2M/170M [00:00<00:00, 162MB/s]
41%|#### | 69.0M/170M [00:00<00:00, 226MB/s]
59%|#####8 | 100M/170M [00:00<00:00, 261MB/s]
77%|#######7 | 131M/170M [00:00<00:00, 282MB/s]
95%|#########5| 162M/170M [00:00<00:00, 296MB/s]
100%|##########| 170M/170M [00:00<00:00, 245MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 1.509 seconds)
+ **Total running time of the script:** ( 2 minutes 52.223 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 66f2e125d..30cc7d499 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 199MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 177MB/s]
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2475 90.1283 94.0255 90.0310 0.4926
+ 90.0721 89.9915 91.6761 89.7874 0.2876
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.233 seconds)
+ **Total running time of the script:** ( 1 minutes 7.798 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 2f48d0836..7bd353466 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.2929 121.1734 126.1004 120.5293 0.6617
+ 122.4077 122.2522 125.8146 120.5202 1.1006
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 54.234 seconds)
+ **Total running time of the script:** ( 1 minutes 55.538 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 fff259b41..b5c4d8887 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 51.377 seconds)
+ **Total running time of the script:** ( 1 minutes 16.194 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 721cefc54..d19553ebb 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5226/132723 [00:00<00:02, 52255.69KB/s]
10%|# | 13337/132723 [00:00<00:01, 69225.95KB/s]
15%|#5 | 20260/132723 [00:00<00:01, 56562.57KB/s]
21%|##1 | 28387/132723 [00:00<00:01, 65150.94KB/s]
26%|##6 | 35156/132723 [00:00<00:01, 49162.78KB/s]
33%|###2 | 43298/132723 [00:00<00:01, 57579.64KB/s]
37%|###7 | 49716/132723 [00:01<00:02, 35441.95KB/s]
43%|####3 | 57732/132723 [00:01<00:01, 43846.61KB/s]
50%|####9 | 65875/132723 [00:01<00:01, 51803.55KB/s]
56%|#####5 | 73934/132723 [00:01<00:01, 58487.45KB/s]
62%|######1 | 81905/132723 [00:01<00:01, 46137.54KB/s]
67%|######7 | 89538/132723 [00:01<00:00, 52318.01KB/s]
74%|#######3 | 97729/132723 [00:01<00:00, 59012.23KB/s]
79%|#######8 | 104670/132723 [00:02<00:00, 53507.85KB/s]
85%|########5 | 112834/132723 [00:02<00:00, 60054.17KB/s]
91%|#########
1| 121004/132723 [00:02<00:00, 65449.27KB/s]
97%|#########7| 129196/132723 [00:02<00:00, 69769.90KB/s]
100%|##########| 132723/132723 [00:02<00:00, 56226.10KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6436/132723 [00:00<00:01, 64343.65KB/s]
11%|#1 | 14793/132723 [00:00<00:01, 75648.52KB/s]
17%|#7 | 23032/132723 [00:00<00:01, 78724.03KB/s]
24%|##3 | 31426/132723 [00:00<00:01, 80781.45KB/s]
30%|##9 | 39505/132723 [00:00<00:01, 79678.83KB/s]
36%|###6 | 47848/132723 [00:00<00:01, 80939.51KB/s]
42%|####2 | 56198/132723 [00:00<00:00, 81767.65KB/s]
49%|####8 | 64625/132723 [00:00<00:00, 82559.17KB/s]
55%|#####4 | 72973/132723 [00:00<00:00, 82844.18KB/s]
61%|######1 | 81335/132723 [00:01<00:00, 83081.40KB/s]
68%|######7 | 89645/132723 [00:01<00:00, 82979.06KB/s]
74%|#######3 | 98017/132723 [00:01<00:00, 83202.55KB/s]
80%|######## | 106393/132723 [00:01<00:00, 83367.31KB/s]
86%|########6 | 114731/132723 [00:01<00:00, 83302.84KB/s]
93%|#########2| 123062/132723 [00:01<00:00, 83205.34KB/s]
99%|########
#8| 131383/132723 [00:01<00:00, 82786.21KB/s]
100%|##########| 132723/132723 [00:01<00:00, 81670.83KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 37.315 seconds)
+ **Total running time of the script:** ( 2 minutes 34.222 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 f45b27f7f..17e8fdb14 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:48.706** total execution time for **how_to_deploy_models** files:
+**10:58.442** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:01.509 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:52.223 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:37.315 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:34.222 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:54.234 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:55.538 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:51.377 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:16.194 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:09.233 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.798 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.265 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.737 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.557 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.065 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.210 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.660 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 80ec1c7fc..294e3e8ed 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipdf73784f-d32a-4c12-a6c5-0dfa4270b97d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipc8243717-03d3-494e-91ab-269d34466cd3 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 cdf10d832..c51d2e952 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:40.102** total execution time for **how_to_extend_tvm** files:
+**00:40.654** 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``) | 00:37.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.566 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.173 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.163 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.900 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.917 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 90d1cbf96..4918687fd 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6785us [6785us] (46.74%; 46.74%)
- FoldScaleAxis: 7732us [5us] (53.26%; 53.26%)
- FoldConstant: 7726us [1569us] (53.23%; 99.93%)
- InferType: 6158us [6158us] (42.42%; 79.70%)
+ InferType: 6702us [6702us] (45.60%; 45.60%)
+ FoldScaleAxis: 7995us [5us] (54.40%; 54.40%)
+ FoldConstant: 7989us [1665us] (54.36%; 99.94%)
+ InferType: 6325us [6325us] (43.03%; 79.16%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6178us [6178us] (44.79%; 44.79%)
- FoldScaleAxis: 7617us [4us] (55.21%; 55.21%)
- FoldConstant: 7613us [1540us] (55.18%; 99.94%)
- InferType: 6073us [6073us] (44.02%; 79.77%)
+ InferType: 6348us [6348us] (43.21%; 43.21%)
+ FoldScaleAxis: 8344us [4us] (56.79%; 56.79%)
+ FoldConstant: 8339us [1659us] (56.76%; 99.95%)
+ InferType: 6680us [6680us] (45.47%; 80.10%)
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 f5042aecf..771a634a8 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.166159 ms
+ Convolution: 44.074540 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 018403a0c..9dca838a0 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.809425 ms
+ conv2d with tensor core: 6.919541 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 76004bf38..cbd3c3c8a 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018610
- Baseline: 3.349917
+ Numpy running time: 0.017816
+ Baseline: 3.257012
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.304482
+ Opt1: 0.295409
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.336753
+ Opt2: 0.330258
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118981
+ Opt3: 0.114631
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110009
+ Opt4: 0.109573
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111204
+ Opt5: 0.111509
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147611
+ Opt6: 0.146465
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 35ce091b5..4cc57adb6 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.571** total execution time for **how_to_optimize_operators** files:
+**00:33.844** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.195 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.663 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.293 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.187 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.084 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.995 | 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 f720871e0..250e85f34 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:10.011** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:18.775** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:26.499 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:34.078 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.581 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.825 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.941 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.323 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.910 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.386 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.648 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.683 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.432 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.481 | 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 2563f8fbd..9af57c5a7 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
@@ -241,216 +241,84 @@ cooperative fetching, unrolling and operator fusion.
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[12] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[6] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[(threadIdx.x_2*3)] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 2)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 336)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 337)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 338)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 672)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 673)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 674)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 1008)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 64512)]
- kernel.shared_1[((threadIdx.x_2*3) + 1009)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 64513)]
- kernel.shared_1[((threadIdx.x_2*3) + 1010)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 64514)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 1344)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1345)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 1346)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 1680)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1681)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 1682)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*3) + 2016)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 129024)]
- kernel.shared_1[((threadIdx.x_2*3) + 2017)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 129025)]
- kernel.shared_1[((threadIdx.x_2*3) + 2018)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 129026)]
- }
- for (rc.outer.inner: int32, 0, 8) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*81) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*81) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (ry.outer.outer*7)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_1) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_1) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_1) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[(threadIdx.x_2*8)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv((floormod(threadIdx.x_2, 3)*8), 3)*9)) + (ry.outer.outer*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 1)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 1), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 2)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 2), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 3)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv((floormod(threadIdx.x_2, 3)*8), 3)*9)) + (ry.outer.outer*3)) + floormod((threadIdx.x_2*2), 3)) + 9)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 4)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 4), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 5)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 5), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 6)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv((floormod(threadIdx.x_2, 3)*8), 3)*9)) + (ry.outer.outer*3)) + floormod((threadIdx.x_2*2), 3)) + 18)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 7)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 7), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ }
+ for (rc.outer.inner: int32, 0, 8) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ }
}
}
}
- for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
}
@@ -505,7 +373,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.265 ms
+ Execution time of this operator: 0.308 ms
@@ -553,36 +421,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=16)
+ 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=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_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)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ 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=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
- compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_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)
@@ -600,16 +468,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=8)
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=112)
+ 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=224)
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=112)
+ 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=224)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -627,195 +495,77 @@ 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__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[2304];
+ extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[504];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 88) {
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((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 * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 3)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 336)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 337)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 338)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 672)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 673)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 674)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1008)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1009)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 64513)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1010)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 64514)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1344)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1345)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1346)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1680)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1681)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1682)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + 2)];
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 3) + 2016)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 129024)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2017)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 129025)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2018)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 129026)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[(((int)threadIdx.x) * 8)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) % 3) * 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 1)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 1) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 2)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 2) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 3)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) % 3) * 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 2) % 3)) + 9)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 4)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 4) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 5)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 5) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 6)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) % 3) * 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 2) % 3)) + 18)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 7)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 7) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ }
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
@@ -869,7 +619,7 @@ In the example below we resume the status and do more 5 trials.
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
Get devices for measurement successfully!
-
+ .T
@@ -877,7 +627,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 26.499 seconds)
+ **Total running time of the script:** ( 3 minutes 34.078 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 8983013cb..1889d753c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7426 9.7360 9.7819 9.7099 0.0298
+ 9.7892 9.7801 9.8291 9.7584 0.0296
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 253f5b4c2..bc1da91ff 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)
- 751.4613 751.3206 752.2142 750.8493 0.5660
+ 748.4140 748.0205 749.2736 747.9480 0.6085
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.581 seconds)
+ **Total running time of the script:** ( 1 minutes 21.825 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 8329f0e70..90a88cf9d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,16 +397,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_1: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.outer.inner*128) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [256], [])[cse_var_1] = 0f32
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
compute_5[(cse_var_1 + 2)] = 0f32
compute_5[(cse_var_1 + 3)] = 0f32
@@ -422,193 +420,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 13)] = 0f32
compute_5[(cse_var_1 + 14)] = 0f32
compute_5[(cse_var_1 + 15)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 64)] = 0f32
- compute_5[(cse_var_1 + 65)] = 0f32
- compute_5[(cse_var_1 + 66)] = 0f32
- compute_5[(cse_var_1 + 67)] = 0f32
- compute_5[(cse_var_1 + 68)] = 0f32
- compute_5[(cse_var_1 + 69)] = 0f32
- compute_5[(cse_var_1 + 70)] = 0f32
- compute_5[(cse_var_1 + 71)] = 0f32
- compute_5[(cse_var_1 + 72)] = 0f32
- compute_5[(cse_var_1 + 73)] = 0f32
- compute_5[(cse_var_1 + 74)] = 0f32
- compute_5[(cse_var_1 + 75)] = 0f32
- compute_5[(cse_var_1 + 76)] = 0f32
- compute_5[(cse_var_1 + 77)] = 0f32
- compute_5[(cse_var_1 + 78)] = 0f32
- compute_5[(cse_var_1 + 79)] = 0f32
- compute_5[(cse_var_1 + 96)] = 0f32
- compute_5[(cse_var_1 + 97)] = 0f32
- compute_5[(cse_var_1 + 98)] = 0f32
- compute_5[(cse_var_1 + 99)] = 0f32
- compute_5[(cse_var_1 + 100)] = 0f32
- compute_5[(cse_var_1 + 101)] = 0f32
- compute_5[(cse_var_1 + 102)] = 0f32
- compute_5[(cse_var_1 + 103)] = 0f32
- compute_5[(cse_var_1 + 104)] = 0f32
- compute_5[(cse_var_1 + 105)] = 0f32
- compute_5[(cse_var_1 + 106)] = 0f32
- compute_5[(cse_var_1 + 107)] = 0f32
- compute_5[(cse_var_1 + 108)] = 0f32
- compute_5[(cse_var_1 + 109)] = 0f32
- compute_5[(cse_var_1 + 110)] = 0f32
- compute_5[(cse_var_1 + 111)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_67: int32 = (elem_idx*16)
- let cse_var_66: int32 = (cse_var_1 + 99)
- let cse_var_65: int32 = (cse_var_1 + 98)
- let cse_var_64: int32 = (cse_var_1 + 97)
- let cse_var_63: int32 = (cse_var_1 + 96)
- let cse_var_62: int32 = (cse_var_1 + 9)
- let cse_var_61: int32 = (cse_var_1 + 8)
- let cse_var_60: int32 = (cse_var_1 + 79)
- let cse_var_59: int32 = (cse_var_1 + 78)
- let cse_var_58: int32 = (cse_var_1 + 77)
- let cse_var_57: int32 = (cse_var_1 + 76)
- let cse_var_56: int32 = (cse_var_1 + 75)
- let cse_var_55: int32 = (cse_var_1 + 74)
- let cse_var_54: int32 = (cse_var_1 + 73)
- let cse_var_53: int32 = (cse_var_1 + 72)
- let cse_var_52: int32 = (cse_var_1 + 71)
- let cse_var_51: int32 = (cse_var_1 + 70)
- let cse_var_50: int32 = (cse_var_1 + 7)
- let cse_var_49: int32 = (cse_var_1 + 69)
- let cse_var_48: int32 = (cse_var_1 + 68)
- let cse_var_47: int32 = (cse_var_1 + 67)
- let cse_var_46: int32 = (cse_var_1 + 66)
- let cse_var_45: int32 = (cse_var_1 + 65)
- let cse_var_44: int32 = (cse_var_1 + 64)
- let cse_var_43: int32 = (cse_var_1 + 6)
- let cse_var_42: int32 = (cse_var_1 + 5)
- let cse_var_41: int32 = (cse_var_1 + 47)
- let cse_var_40: int32 = (cse_var_1 + 46)
- let cse_var_39: int32 = (cse_var_1 + 45)
- let cse_var_38: int32 = (cse_var_1 + 44)
- let cse_var_37: int32 = (cse_var_1 + 43)
- let cse_var_36: int32 = (cse_var_1 + 42)
- let cse_var_35: int32 = (cse_var_1 + 41)
- let cse_var_34: int32 = (cse_var_1 + 40)
- let cse_var_33: int32 = (cse_var_1 + 4)
- let cse_var_32: int32 = (cse_var_1 + 39)
- let cse_var_31: int32 = (cse_var_1 + 38)
- let cse_var_30: int32 = (cse_var_1 + 37)
- let cse_var_29: int32 = (cse_var_1 + 36)
- let cse_var_28: int32 = (cse_var_1 + 35)
- let cse_var_27: int32 = (cse_var_1 + 34)
- let cse_var_26: int32 = (cse_var_1 + 33)
- let cse_var_25: int32 = (cse_var_1 + 32)
- let cse_var_24: int32 = (cse_var_1 + 3)
- let cse_var_23: int32 = (cse_var_1 + 2)
- let cse_var_22: int32 = (cse_var_1 + 15)
- let cse_var_21: int32 = (cse_var_1 + 14)
- let cse_var_20: int32 = (cse_var_1 + 13)
- let cse_var_19: int32 = (cse_var_1 + 12)
- let cse_var_18: int32 = (cse_var_1 + 111)
- let cse_var_17: int32 = (cse_var_1 + 110)
- let cse_var_16: int32 = (cse_var_1 + 11)
- let cse_var_15: int32 = (cse_var_1 + 109)
- let cse_var_14: int32 = (cse_var_1 + 108)
- let cse_var_13: int32 = (cse_var_1 + 107)
- let cse_var_12: int32 = (cse_var_1 + 106)
- let cse_var_11: int32 = (cse_var_1 + 105)
- let cse_var_10: int32 = (cse_var_1 + 104)
- let cse_var_9: int32 = (cse_var_1 + 103)
- let cse_var_8: int32 = (cse_var_1 + 102)
- let cse_var_7: int32 = (cse_var_1 + 101)
- let cse_var_6: int32 = (cse_var_1 + 100)
- let cse_var_5: int32 = (cse_var_1 + 10)
- let cse_var_4: int32 = (cse_var_1 + 1)
- let cse_var_3: int32 = ((i0.outer*2048) + (i.outer.inner*1024))
- {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_67)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- }
+ }
+ }
+ for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
+ for (i.inner: int32, 0, 8) {
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_2: int32 = ((i.outer.inner*128) + (i.inner*16))
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + 1)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_4: int32 = (((i.outer.inner*128) + (i.inner*16)) + 2)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*128) + (i.inner*16)) + 3)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*128) + (i.inner*16)) + 4)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*128) + (i.inner*16)) + 5)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*128) + (i.inner*16)) + 6)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*128) + (i.inner*16)) + 7)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*128) + (i.inner*16)) + 8)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*128) + (i.inner*16)) + 9)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*128) + (i.inner*16)) + 10)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*128) + (i.inner*16)) + 11)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*128) + (i.inner*16)) + 12)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*128) + (i.inner*16)) + 13)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*128) + (i.inner*16)) + 14)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*128) + (i.inner*16)) + 15)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_68: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*32))
- compute[ramp(cse_var_68, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+ compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -664,7 +549,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 3.019 ms
+ Execution time of this operator: 1.844 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 63371cad0..35083c489 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:46.845** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.368** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.809 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.334 | 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``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 973b6cff0..e082bda56 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 194.69/194.69 result: MeasureResult(costs=(0.0011890512222222224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0911288261413574, timestamp=1661412805.2547846) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/194.69 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 174.77/174.77 result: MeasureResult(costs=(0.0013245948555555556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0623905658721924, timestamp=1661426185.0137548) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/174.77 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 259.81/259.81 result: MeasureResult(costs=(0.0008910316574585634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7313928604125977, timestamp=1661412806.162532) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 259.92/259.92 result: MeasureResult(costs=(0.0008906486243093922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7344768047332764, timestamp=1661426185.9444644) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.29/259.81 result: MeasureResult(costs=(0.043743752000000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8454883098602295, timestamp=1661412810.7189252) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.34/259.81 result: MeasureResult(costs=(0.069390816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.541620492935181, timestamp=1661412811.9708114) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.30/259.92 result: MeasureResult(costs=(0.043681782499999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7933611869812012, timestamp=1661426190.4473178) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/259.92 result: MeasureResult(costs=(0.06939374050000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.509384632110596, timestamp=1661426191.688685) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.03/259.81 result: MeasureResult(costs=(0.008257752857142859,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.258805513381958, timestamp=1661412823.0187645) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 27.93/259.92 result: MeasureResult(costs=(0.008289639357142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2552039623260498, timestamp=1661426202.725381) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001277
+ Time cost of this operator: 0.001272
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 a43fcb871..dcea27e68 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.1 98.725 (1, 2, 10, 10, 3) 2 1 [309.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.024 0.966 (1, 6, 10, 10) 1 1 [3.024]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.309 (1, 1, 10, 10, 3) 1 1 [0.968]
- Total_time - 313.092 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.4 98.732 (1, 2, 10, 10, 3) 2 1 [313.4]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.064 0.965 (1, 6, 10, 10) 1 1 [3.064]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.303 (1, 1, 10, 10, 3) 1 1 [0.961]
+ Total_time - 317.425 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 120.6 97.797 (1, 6, 10, 10, 1) 2 1 [120.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.744 1.414 (1, 6, 10, 10) 1 1 [1.744]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.789 (1, 1, 10, 10, 3) 1 1 [0.973]
- Total_time - 123.317 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 130.1 97.938 (1, 6, 10, 10, 1) 2 1 [130.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.786 1.345 (1, 6, 10, 10) 1 1 [1.786]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.718 (1, 1, 10, 10, 3) 1 1 [0.953]
+ Total_time - 132.84 - - - - -
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 bb15d6cc4..e12ef7337 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpxxco06av/images/random'
+ '/tmp/tmpknjo1lwr/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpxxco06av/images/target contains 8144 images
- /tmp/tmpxxco06av/images/random contains 5000 images
+ /tmp/tmpknjo1lwr/images/target contains 8144 images
+ /tmp/tmpknjo1lwr/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2094 - accuracy: 0.9294 - val_loss: 0.1389 - val_accuracy: 0.9577
+ 328/328 - 55s - loss: 0.2134 - accuracy: 0.9251 - val_loss: 0.1621 - val_accuracy: 0.9569
Epoch 2/3
- 328/328 - 52s - loss: 0.0934 - accuracy: 0.9656 - val_loss: 0.1387 - val_accuracy: 0.9532
+ 328/328 - 52s - loss: 0.1061 - accuracy: 0.9599 - val_loss: 0.1173 - val_accuracy: 0.9637
Epoch 3/3
- 328/328 - 52s - loss: 0.0687 - accuracy: 0.9742 - val_loss: 0.1056 - val_accuracy: 0.9694
+ 328/328 - 52s - loss: 0.0704 - accuracy: 0.9745 - val_loss: 0.1219 - val_accuracy: 0.9569
- <keras.callbacks.History object at 0x7f20286e0790>
+ <keras.callbacks.History object at 0x7f6df5c2e810>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 16.243 seconds)
+ **Total running time of the script:** ( 4 minutes 28.979 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 2397d7fd7..e6755b5f8 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**06:08.954** total execution time for **how_to_work_with_microtvm** files:
+**05:20.896** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:16.243 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:28.979 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.884 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.408 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.544 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.290 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.282 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.217 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index b4452fb19..087be5265 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
=================
-**00:38.376** total execution time for **how_to_work_with_relay** files:
+**00:42.776** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.015 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.380 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:04.917 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.968 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.437 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.420 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index f28ca04c9..f69c2b516 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f1f9384e440>
+ <function my_cuda_math_rule at 0x7f6d7fe81200>
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 3a3be48e0..419df796d 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
Computation times
=================
-**00:04.499** total execution time for **how_to_work_with_schedules** files:
+**00:04.028** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.055 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.859 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.129 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.958 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.572 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.524 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.556 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.506 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.103 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.042 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index fb0cc18cb..1e20b39b0 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpx6do_wif/input0.cc'\nsource_filename = \"/tmp/tmpx6do_wif/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp8das6brp/input0.cc'\nsource_filename = \"/tmp/tmp8das6brp/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index bbaf70fa8..41cd27575 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:20.791** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.005** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.785 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.999 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 2d28a6357..9586b578c 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.10s!
+ resnet18_v1 inference graph built in 22.46s!
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 890428ea9..de7640d9c 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.63s!
+ yolov3-tiny inference graph built in 15.92s!
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 32f20c903..ce335b691 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:30.922** total execution time for **topic_vta_tutorials_frontend** files:
+**01:29.384** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.495 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.184 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.426 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.200 | 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 07f19c30a..9dbd1330b 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
=================
-**00:03.313** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.258** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.881 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.862 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.432 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.396 | 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 cbb5b36c3..952da6fc0 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.781** total execution time for **topic_vta_tutorials** files:
+**00:00.714** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.409 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.384 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.372 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.330 | 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 679d05fcb..593e4e633 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.756 ms
+ Execution time of this operator: 94.166 ms
@@ -442,11 +442,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 6.084 seconds)
-
-
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
.. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 402e17c78..900cf55c7 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.11/9.11 result: MeasureResult(costs=(0.0294744746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6073787212371826, timestamp=1661411553.6023083) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.51/9.11 result: MeasureResult(costs=(0.10700922419999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.860762357711792, timestamp=1661411555.4756367) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.022767709400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.549781322479248, timestamp=1661411556.5442965) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.79 result: MeasureResult(costs=(0.1451199476,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4403741359710693, timestamp=1661411559.0312407) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.65/11.79 result: MeasureResult(costs=(0.0735167652,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3179419040679932, timestamp=1661411560.4768026) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.82/11.79 result: MeasureResult(costs=(0.14732233060000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4836344718933105, timestamp=1661411563.5380652) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.86/11.79 result: MeasureResult(costs=(0.3105263904,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0938615798950195, timestamp=1661411569.2138937) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.15/11.79 result: MeasureResult(costs=(0.0264373262,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5743741989135742, timestamp=1661411569.8078992) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.91/11.79 result: MeasureResult(costs=(0.1406850224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3574085235595703, timestamp=1661411572.2871306) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.77/11.79 result: MeasureResult(costs=(0.0968905154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6575357913970947, timestamp=1661411574.001657) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.77/10.77 result: MeasureResult(costs=(0.024922450399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.532639741897583, timestamp=1661425007.8455124) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.93/10.77 result: MeasureResult(costs=(0.09165923699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6069185733795166, timestamp=1661425009.4760969) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.022665557,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5586798191070557, timestamp=1661425010.5272446) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.45/11.84 result: MeasureResult(costs=(0.18519991819999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.087189197540283, timestamp=1661425014.1780627) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.46/11.84 result: MeasureResult(costs=(0.0776558006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3820717334747314, timestamp=1661425015.6873703) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.46/11.84 result: MeasureResult(costs=(0.1835167872,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1046082973480225, timestamp=1661425018.836185) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.86/11.84 result: MeasureResult(costs=(0.3104250466,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.087313890457153, timestamp=1661425024.495183) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.70/11.84 result: MeasureResult(costs=(0.025083290199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5430276393890381, timestamp=1661425025.0586967) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.74/11.84 result: MeasureResult(costs=(0.154582941,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.574871778488159, timestamp=1661425027.7539246) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.65/11.84 result: MeasureResult(costs=(0.1012859838,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.724215030670166, timestamp=1661425029.5370471) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index f512b05ad..2786151cf 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 498.8148181299857, 'median': 498.6909075999847, 'std': 0.5668175327660779}
+ {'mean': 490.990710279998, 'median': 490.65708260000065, 'std': 1.161852073224186}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (4/20) | 5.93 s
[Task 1/25] Current/Best: 6.16/ 17.45 GFLOPS | Progress: (8/20) | 9.53 s
[Task 1/25] Current/Best: 11.51/ 22.76 GFLOPS | Progress: (12/20) | 11.98 s
[Task 1/25] Current/Best: 16.44/ 22.76 GFLOPS | Progress: (16/20) | 13.68 s
[Task 1/25] Current/Best: 11.57/ 23.82 GFLOPS | Progress: (20/20) | 15.42 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.08/ 12.90 GFLOPS | Progress: (4/20) | 3.88 s
[Task 2/25] Current/Best: 14.26/ 18.00 GFLOPS | Progress: (8/20) | 5.18 s
[Task 2/25] Current/Best: 21.28/ 21.28 GFLOPS | Progress: (12/20) | 6.51 s
[Task 2/25] Current/Best: 12.23/ 21.28 GFLOPS | Progress: (16/20) | 7.76 s
[Task 2/25] Current/Best: 19.39/ 21.28 GFLOPS | Progress: (20/20) | 9.40 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.80 GFLOPS | Progress: (4/20) | 5.92 s
[Task 3/25] Current/Best: 15.31/ 16.81 GFLOPS | Progress: (8/20) | 7.85 s
[Task 3/25] Current/Best: 14.97/ 16.81 GFLOPS | Progress: (12/20) | 9.62 s
[Task 3/25] Current/Best: 7.14/ 23.71 GFLOPS | Progress: (16/20) | 11.54 s
[Task 3/25] Current/Best: 12.12/ 23.71 GFLOPS | Progress: (20/20) | 16.09 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.53/ 20.31 GFLOPS | Progress: (4/20) | 2.46 s
[Task 4/25] Current/Best: 6.53/ 20.31 GFLOPS | Progress: (8/20) | 6.89 s
[Task 4/25] Current/Best: 21.93/ 21.93 GFLOPS | Progress: (12/20) | 11.54 s
[Task 4/25] Current/Best: 15.27/ 21.93 GFLOPS | Progress: (16/20) | 13.82 s
[Task 4/25] Current/Best: 13.40/ 21.93 GFLOPS | Progress: (20/20) | 15.73 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.59/ 10.15 GFLOPS | Progress: (4/20) | 2.66 s
[Task 5/25] Current/Best: 11.52/ 12.42 GFLOPS | Progress: (8/20) | 4.75 s
[Task 5/25] Current/Best: 11.04/ 18.01 GFLOPS | Progress: (12/20) | 7.74 s
[Task 5/25] Current/Best: 11.91/ 22.53 GFLOPS | Progress: (16/20) | 9.16 s
[Task 5/25] Current/Best: 12.07/ 22.53 GFLOPS | Progress: (20/20) | 11.05 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.10/ 20.68 GFLOPS | Progress: (4/20) | 4.07 s
[Task 6/25] Current/Best: 18.94/ 20.68 GFLOPS | Progress: (8/20) | 5.82 s
[Task 6/25] Current/Best: 13.17/ 20.68 GFLOPS | Progress: (12/20) | 7.76 s
[Task 6/25] Current/Best: 19.93/ 20.68 GFLOPS | Progress: (16/20) | 10.02 s
[Task 6/25] Current/Best: 3.73/ 20.68 GFLOPS | Progress: (20/20) | 12.54 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.11/ 12.89 GFLOPS | Progress: (4/20) | 3.71 s
[Task 7/25] Current/Best: 20.19/ 20.90 GFLOPS | Progress: (8/20) | 5.25 s
[Task 7/25] Current/Best: 15.89/ 20.90 GFLOPS | Progress: (12/20) | 7.17 s
[Task 7/25] Current/Best: 12.24/ 20.90 GFLOPS | Progress: (16/20) | 9.24 s
[Task 7/25] Current/Best: 6.40/ 21.69 GFLOPS | Progress: (20/20) | 11.72 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.14/ 13.96 GFLOPS | Progress: (4/20) | 3.00 s
[Task 8/25] Current/Best: 9.62/ 13.96 GFLOPS | Progress: (8/20) | 7.79 s
[Task 8/25] Current/Best: 13.03/ 13.96 GFLOPS | Progress: (12/20) | 13.99 s
[Task 8/25] Current/Best: 18.76/ 18.76 GFLOPS | Progress: (16/20) | 16.11 s
[Task 8/25] Current/Best: 19.72/ 19.72 GFLOPS | Progress: (20/20) | 22.76 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.28/ 14.95 GFLOPS | Progress: (4/20) | 12.03 s
[Task 9/25] Current/Best: 23.28/ 23.28 GFLOPS | Progress: (8/20) | 13.85 s
[Task 9/25] Current/Best: 8.24/ 23.28 GFLOPS | Progress: (12/20) | 16.25 s
[Task 9/25] Current/Best: 17.86/ 23.28 GFLOPS | Progress: (16/20) | 18.96 s
[Task 9/25] Current/Best: 9.19/ 23.28 GFLOPS | Progress: (20/20) | 26.84 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.42/ 18.42 GFLOPS | Progress: (4/20) | 2.62 s
[Task 10/25] Current/Best: 15.50/ 18.42 GFLOPS | Progress: (8/20) | 4.25 s
[Task 10/25] Current/Best: 12.35/ 19.25 GFLOPS | Progress: (12/20) | 5.79 s
[Task 10/25] Current/Best: 19.14/ 20.39 GFLOPS | Progress: (16/20) | 6.91 s
[Task 10/25] Current/Best: 8.83/ 20.39 GFLOPS | Progress: (20/20
) | 8.47 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.36/ 18.26 GFLOPS | Progress: (4/20) | 3.40 s
[Task 11/25] Current/Best: 16.67/ 18.26 GFLOPS | Progress: (8/20) | 6.15 s
[Task 11/25] Current/Best: 18.16/ 18.26 GFLOPS | Progress: (12/20) | 8.20 s
[Task 11/25] Current/Best: 13.46/ 20.94 GFLOPS | Progress: (16/20) | 10.94 s
[Task 11/25] Current/Best: 19.45/ 21.62 GFLOPS | Progress: (20/20) | 12.99 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.20 GFLOPS | Progress: (4/20) | 5.43 s
[Task 12/25] Current/Best: 5.21/ 18.20 GFLOPS | Progress: (8/20) | 9.14 s
[Task 12/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (12/20) | 11.14 s
[Task 12/25] Current/Best: 15.10/ 19.04 GFLOPS | Progress: (16/20) | 13.96 s
[Task 12/25] Current/Best: 15.08/ 19.04 GFLOPS | Progress: (20/20) | 15.93 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.67/ 17.14 GFLOPS | Progress: (4/20) | 3.78 s
[Task 13/25] Current/Best: 15.60/ 20.86 GFLOPS | Progress: (8/20) | 6.24 s
[Task 13/25] Current/Best: 19.67/ 21.30 GFLOPS | Progress: (12/20) | 9.15 s
[Task 13/25] Current/Best: 12.21/ 21.30 GFLOPS | Progress: (16/20) | 12.56 s
[Task 13/25] Current/Best: 18.52/ 21.30 GFLOPS | Progress: (20/20) | 14.80 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (4/20) | 3.38 s
[Task 14/25] Current/Best: 6.08/ 13.64 GFLOPS | Progress: (8/20) | 5.56 s
[Task 14/25] Current/Best: 20.05/ 20.05 GFLOPS | Progress: (12/20) | 8.12 s
[Task 14/25] Current/Best: 17.32/ 20.05 GFLOPS | Progress: (16/20) | 9.81 s Done.
-
[Task 14/25] Current/Best: 17.02/ 20.05 GFLOPS | Progress: (20/20) | 11.61 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.19/ 17.62 GFLOPS | Progress: (4/20) | 2.82 s
[Task 15/25] Current/Best: 14.32/ 17.97 GFLOPS | Progress: (8/20) | 4.12 s
[Task 15/25] Current/Best: 10.35/ 22.31 GFLOPS | Progress: (12/20) | 6.23 s
[Task 15/25] Current/Best: 20.23/ 22.31 GFLOPS | Progress: (16/20) | 9.22 s
[Task 15/25] Current/Best: 9.66/ 22.31 GFLOPS | Progress: (20/20) | 10.20 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (4/20) | 3.03 s
[Task 16/25] Current/Best: 3.04/ 20.46 GFLOPS | Progress: (8/20) | 4.68 s
[Task 16/25] Current/Best: 18.78/ 20.46 GFLOPS | Progress: (12/20) | 5.91 s
[Task 16/25] Current/Best: 17.59/ 20.46 GFLOPS | Progress: (16/20) |
7.26 s
[Task 16/25] Current/Best: 10.04/ 21.80 GFLOPS | Progress: (20/20) | 9.34 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.06/ 18.31 GFLOPS | Progress: (4/20) | 4.79 s
[Task 17/25] Current/Best: 14.43/ 23.17 GFLOPS | Progress: (8/20) | 7.69 s
[Task 17/25] Current/Best: 17.93/ 23.17 GFLOPS | Progress: (12/20) | 9.75 s
[Task 17/25] Current/Best: 16.38/ 23.17 GFLOPS | Progress: (16/20) | 11.91 s
[Task 17/25] Current/Best: 10.02/ 23.17 GFLOPS | Progress: (20/20) | 14.06 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.55/ 17.06 GFLOPS | Progress: (4/20) | 3.79 s
[Task 18/25] Current/Best: 10.52/ 19.03 GFLOPS | Progress: (8/20) | 7.30 s
[Task 18/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (12/20) | 9.27 s
[Task 18/25] Current/Best: 10.02/ 19.04 GFLOPS | Progress: (16/20) | 12.90 s
[Task 18/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (20/20) | 14.41 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.83/ 20.35 GFLOPS | Progress: (4/20) | 6.18 s
[Task 19/25] Current/Best: 2.69/ 20.35 GFLOPS | Progress: (8/20) | 9.46 s
[Task 19/25] Current/Best: 19.85/ 21.16 GFLOPS | Progress: (12/20) | 12.26 s
[Task 19/25] Current/Best: 15.30/ 21.68 GFLOPS | Progress: (16/20) | 15.08 s
[Task 19/25] Current/Best: 2.70/ 22.49 GFLOPS | Progress: (20/20) | 17.89 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.51/ 15.08 GFLOPS | Progress: (4/20) | 3.39 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.57/ 17.57 GFLOPS | Progress: (4/20) | 6.30 s
[Task 1/25] Current/Best: 6.16/ 17.57 GFLOPS | Progress: (8/20) | 9.32 s
[Task 1/25] Current/Best: 11.53/ 22.69 GFLOPS | Progress: (12/20) | 11.74 s
[Task 1/25] Current/Best: 16.54/ 22.87 GFLOPS | Progress: (16/20) | 13.42 s
[Task 1/25] Current/Best: 11.60/ 23.86 GFLOPS | Progress: (20/20) | 15.15 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.28/ 13.36 GFLOPS | Progress: (4/20) | 3.81 s
[Task 2/25] Current/Best: 14.25/ 18.80 GFLOPS | Progress: (8/20) | 5.09 s
[Task 2/25] Current/Best: 21.00/ 21.00 GFLOPS | Progress: (12/20) | 6.40 s
[Task 2/25] Current/Best: 12.10/ 21.00 GFLOPS | Progress: (16/20) | 7.65 s
[Task 2/25] Current/Best: 18.63/ 21.00 GFLOPS | Progress: (20/20) | 9.23 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.84 GFLOPS | Progress: (4/20) | 5.86 s
[Task 3/25] Current/Best: 15.36/ 16.81 GFLOPS | Progress: (8/20) | 7.78 s
[Task 3/25] Current/Best: 15.00/ 16.81 GFLOPS | Progress: (12/20) | 9.48 s
[Task 3/25] Current/Best: 7.23/ 23.77 GFLOPS | Progress: (16/20) | 11.40 s
[Task 3/25] Current/Best: 12.63/ 23.77 GFLOPS | Progress: (20/20) | 15.93 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.40/ 18.03 GFLOPS | Progress: (4/20) | 2.41 s
[Task 4/25] Current/Best: 6.83/ 18.03 GFLOPS | Progress: (8/20) | 6.79 s
[Task 4/25] Current/Best: 22.13/ 22.13 GFLOPS | Progress: (12/20) | 11.30 s
[Task 4/25] Current/Best: 16.54/ 22.13 GFLOPS | Progress: (16/20) | 13.55 s
[Task 4/25] Current/Best: 13.34/ 22.13 GFLOPS | Progress: (20/20) | 15.53 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.43/ 10.25 GFLOPS | Progress: (4/20) | 2.61 s
[Task 5/25] Current/Best: 11.73/ 12.76 GFLOPS | Progress: (8/20) | 4.68 s
[Task 5/25] Current/Best: 11.87/ 18.13 GFLOPS | Progress: (12/20) | 7.76 s
[Task 5/25] Current/Best: 11.77/ 22.47 GFLOPS | Progress: (16/20) | 9.20 s
[Task 5/25] Current/Best: 11.93/ 22.47 GFLOPS | Progress: (20/20) | 11.05 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.16/ 20.71 GFLOPS | Progress: (4/20) | 3.96 s
[Task 6/25] Current/Best: 19.01/ 20.71 GFLOPS | Progress: (8/20) | 5.72 s
[Task 6/25] Current/Best: 13.36/ 20.71 GFLOPS | Progress: (12/20) | 7.64 s
[Task 6/25] Current/Best: 19.99/ 20.71 GFLOPS | Progress: (16/20) | 9.89 s
[Task 6/25] Current/Best: 3.72/ 20.71 GFLOPS | Progress: (20/20) | 12.40 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.03/ 12.92 GFLOPS | Progress: (4/20) | 3.53 s
[Task 7/25] Current/Best: 20.25/ 21.09 GFLOPS | Progress: (8/20) | 5.04 s
[Task 7/25] Current/Best: 15.96/ 21.09 GFLOPS | Progress: (12/20) | 6.94 s
[Task 7/25] Current/Best: 12.26/ 21.09 GFLOPS | Progress: (16/20) | 8.98 s
[Task 7/25] Current/Best: 6.34/ 21.80 GFLOPS | Progress: (20/20) | 11.45 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.43/ 14.05 GFLOPS | Progress: (4/20) | 2.93 s
[Task 8/25] Current/Best: 9.17/ 14.05 GFLOPS | Progress: (8/20) | 7.80 s
[Task 8/25] Current/Best: 12.61/ 14.05 GFLOPS | Progress: (12/20) | 13.93 s
[Task 8/25] Current/Best: 18.72/ 18.72 GFLOPS | Progress: (16/20) | 16.02 s
[Task 8/25] Current/Best: 19.55/ 19.55 GFLOPS | Progress: (20/20) | 22.59 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.31/ 15.40 GFLOPS | Progress: (4/20) | 11.95 s
[Task 9/25] Current/Best: 23.47/ 23.47 GFLOPS | Progress: (8/20) | 13.75 s
[Task 9/25] Current/Best: 8.25/ 23.47 GFLOPS | Progress: (12/20) | 16.10 s
[Task 9/25] Current/Best: 17.70/ 23.47 GFLOPS | Progress: (16/20) | 18.75 s
[Task 9/25] Current/Best: 9.22/ 23.47 GFLOPS | Progress: (20/20) | 26.38 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.60 s
[Task 10/25] Current/Best: 15.53/ 18.20 GFLOPS | Progress: (8/20) | 4.16 s
[Task 10/25] Current/Best: 12.34/ 18.92 GFLOPS | Progress: (12/20) | 5.68 s
[Task 10/25] Current/Best: 19.19/ 20.23 GFLOPS | Progress: (16/20) | 6.79 s
[Task 10/25] Current/Best: 8.78/ 20.23 GFLOPS | Progress: (20/20
) | 8.32 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.30/ 18.27 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 15.86/ 18.27 GFLOPS | Progress: (8/20) | 6.06 s
[Task 11/25] Current/Best: 17.91/ 18.27 GFLOPS | Progress: (12/20) | 8.13 s
[Task 11/25] Current/Best: 13.58/ 20.95 GFLOPS | Progress: (16/20) | 10.84 s
[Task 11/25] Current/Best: 19.45/ 21.61 GFLOPS | Progress: (20/20) | 12.88 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.84/ 17.87 GFLOPS | Progress: (4/20) | 5.35 s
[Task 12/25] Current/Best: 5.23/ 17.87 GFLOPS | Progress: (8/20) | 9.01 s
[Task 12/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (12/20) | 11.01 s
[Task 12/25] Current/Best: 15.47/ 18.91 GFLOPS | Progress: (16/20) | 13.76 s
[Task 12/25] Current/Best: 15.12/ 18.91 GFLOPS | Progress: (20/20) | 15.68 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.87/ 17.29 GFLOPS | Progress: (4/20) | 3.64 s
[Task 13/25] Current/Best: 14.89/ 21.03 GFLOPS | Progress: (8/20) | 6.07 s
[Task 13/25] Current/Best: 19.72/ 21.36 GFLOPS | Progress: (12/20) | 9.01 s
[Task 13/25] Current/Best: 12.29/ 21.36 GFLOPS | Progress: (16/20) | 12.40 s
[Task 13/25] Current/Best: 18.69/ 21.36 GFLOPS | Progress: (20/20) | 14.65 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.73/ 13.73 GFLOPS | Progress: (4/20) | 3.24 s
[Task 14/25] Current/Best: 6.12/ 13.73 GFLOPS | Progress: (8/20) | 5.44 s
[Task 14/25] Current/Best: 19.97/ 19.97 GFLOPS | Progress: (12/20) | 7.99 s
[Task 14/25] Current/Best: 17.39/ 19.97 GFLOPS | Progress: (16/20) | 9.64 s Done.
+
[Task 14/25] Current/Best: 17.28/ 19.97 GFLOPS | Progress: (20/20) | 11.39 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.17/ 17.66 GFLOPS | Progress: (4/20) | 2.74 s
[Task 15/25] Current/Best: 14.51/ 17.99 GFLOPS | Progress: (8/20) | 4.08 s
[Task 15/25] Current/Best: 10.37/ 22.35 GFLOPS | Progress: (12/20) | 6.14 s
[Task 15/25] Current/Best: 20.35/ 22.35 GFLOPS | Progress: (16/20) | 9.08 s
[Task 15/25] Current/Best: 9.69/ 22.35 GFLOPS | Progress: (20/20) | 10.05 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (4/20) | 2.94 s
[Task 16/25] Current/Best: 3.00/ 20.26 GFLOPS | Progress: (8/20) | 4.56 s
[Task 16/25] Current/Best: 18.76/ 20.26 GFLOPS | Progress: (12/20) | 5.79 s
[Task 16/25] Current/Best: 17.42/ 20.26 GFLOPS | Progress: (16/20) |
7.12 s
[Task 16/25] Current/Best: 10.01/ 21.93 GFLOPS | Progress: (20/20) | 9.14 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.99/ 18.39 GFLOPS | Progress: (4/20) | 4.69 s
[Task 17/25] Current/Best: 14.16/ 23.29 GFLOPS | Progress: (8/20) | 7.46 s
[Task 17/25] Current/Best: 17.15/ 23.29 GFLOPS | Progress: (12/20) | 9.52 s
[Task 17/25] Current/Best: 16.59/ 23.29 GFLOPS | Progress: (16/20) | 11.65 s
[Task 17/25] Current/Best: 10.04/ 23.29 GFLOPS | Progress: (20/20) | 13.77 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.33/ 17.96 GFLOPS | Progress: (4/20) | 3.68 s
[Task 18/25] Current/Best: 10.61/ 17.96 GFLOPS | Progress: (8/20) | 7.11 s
[Task 18/25] Current/Best: 19.26/ 19.26 GFLOPS | Progress: (12/20) | 9.03 s
[Task 18/25] Current/Best: 10.04/ 19.26 GFLOPS | Progress: (16/20) | 12.59 s
[Task 18/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (20/20) | 14.11 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.16/ 20.27 GFLOPS | Progress: (4/20) | 6.00 s
[Task 19/25] Current/Best: 2.69/ 20.27 GFLOPS | Progress: (8/20) | 9.28 s
[Task 19/25] Current/Best: 18.71/ 21.69 GFLOPS | Progress: (12/20) | 12.11 s
[Task 19/25] Current/Best: 14.08/ 21.69 GFLOPS | Progress: (16/20) | 15.00 s
[Task 19/25] Current/Best: 2.70/ 23.34 GFLOPS | Progress: (20/20) | 17.89 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.01/ 15.11 GFLOPS | Progress: (4/20) | 3.33 s Done.
Done.
-
[Task 20/25] Current/Best: 10.49/ 15.08 GFLOPS | Progress: (8/20) | 6.85 s
[Task 20/25] Current/Best: 2.32/ 15.08 GFLOPS | Progress: (12/20) | 10.80 s
[Task 20/25] Current/Best: 12.44/ 15.08 GFLOPS | Progress: (16/20) | 14.37 s
[Task 20/25] Current/Best: 13.14/ 21.89 GFLOPS | Progress: (20/20) | 16.48 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.66 GFLOPS | Progress: (4/20) | 3.30 s
[Task 21/25] Current/Best: 14.57/ 17.66 GFLOPS | Progress: (8/20) | 4.91 s
[Task 21/25] Current/Best: 1.61/ 17.66 GFLOPS | Progress: (12/20) | 7.08 s
[Task 21/25] Current/Best: 17.85/ 17.85 GFLOPS | Progress: (16/20) | 10.61 s
[Task 21/25] Current/Best: 4.47/ 17.85 GFLOPS | Progress: (20/20) | 17.66 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.11 GFLOPS | Progress: (4/20
) | 2.75 s
[Task 22/25] Current/Best: 8.81/ 21.92 GFLOPS | Progress: (8/20) | 4.74 s
[Task 22/25] Current/Best: 19.95/ 21.92 GFLOPS | Progress: (12/20) | 7.05 s
[Task 22/25] Current/Best: 15.24/ 21.92 GFLOPS | Progress: (16/20) | 9.11 s
[Task 22/25] Current/Best: 14.26/ 21.92 GFLOPS | Progress: (20/20) | 10.79 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.45/ 20.36 GFLOPS | Progress: (4/20) | 3.30 s
[Task 23/25] Current/Best: 15.53/ 20.36 GFLOPS | Progress: (8/20) | 6.67 s
[Task 23/25] Current/Best: 20.86/ 21.42 GFLOPS | Progress: (12/20) | 8.51 s
[Task 23/25] Current/Best: 6.37/ 21.42 GFLOPS | Progress: (16/20) | 15.67 s
[Task 23/25] Current/Best: 7.63/ 21.42 GFLOPS | Progress: (20/20) | 19.92 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.29/ 8.29 GFLOPS | Progress: (4/20) | 11.86 s
[Task 24/25] Current/Best: 2.04/ 8.29 GFLOPS | Progress: (8/20) | 22.94 s
[Task 24/25] Current/Best: 4.55/ 8.29 GFLOPS | Progress: (12/20) | 34.52 s Done.
-
[Task 24/25] Current/Best: 6.58/ 8.67 GFLOPS | Progress: (16/20) | 40.19 s
[Task 24/25] Current/Best: 3.33/ 8.67 GFLOPS | Progress: (20/20) | 46.13 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.86 GFLOPS | Progress: (4/20) | 11.65 s
[Task 25/25] Current/Best: 5.67/ 7.71 GFLOPS | Progress: (8/20) | 22.99 s
[Task 25/25] Current/Best: 5.86/ 7.71 GFLOPS | Progress: (12/20) | 34.46 s
[Task 25/25] Current/Best: 5.72/ 8.46 GFLOPS | Progress: (16/20) | 36.21 s
[Task 25/25] Current/Best: 2.81/ 8.67 GFLOPS | Progress: (20/20) | 46.90 s
+
[Task 20/25] Current/Best: 9.65/ 15.11 GFLOPS | Progress: (8/20) | 6.67 s
[Task 20/25] Current/Best: 2.27/ 15.33 GFLOPS | Progress: (12/20) | 10.60 s
[Task 20/25] Current/Best: 12.26/ 15.33 GFLOPS | Progress: (16/20) | 14.33 s
[Task 20/25] Current/Best: 12.49/ 22.26 GFLOPS | Progress: (20/20) | 16.40 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.68 GFLOPS | Progress: (4/20) | 3.23 s
[Task 21/25] Current/Best: 14.65/ 17.68 GFLOPS | Progress: (8/20) | 4.78 s
[Task 21/25] Current/Best: 1.61/ 17.68 GFLOPS | Progress: (12/20) | 6.92 s
[Task 21/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (16/20) | 10.36 s
[Task 21/25] Current/Best: 4.48/ 18.04 GFLOPS | Progress: (20/20) | 17.42 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.08 GFLOPS | Progress: (4/20
) | 2.68 s
[Task 22/25] Current/Best: 8.64/ 21.85 GFLOPS | Progress: (8/20) | 4.67 s
[Task 22/25] Current/Best: 20.04/ 21.85 GFLOPS | Progress: (12/20) | 6.99 s
[Task 22/25] Current/Best: 15.43/ 21.85 GFLOPS | Progress: (16/20) | 9.02 s
[Task 22/25] Current/Best: 13.95/ 21.85 GFLOPS | Progress: (20/20) | 10.73 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.76/ 20.91 GFLOPS | Progress: (4/20) | 3.26 s
[Task 23/25] Current/Best: 14.08/ 20.91 GFLOPS | Progress: (8/20) | 6.54 s
[Task 23/25] Current/Best: 20.98/ 21.79 GFLOPS | Progress: (12/20) | 8.33 s
[Task 23/25] Current/Best: 6.38/ 21.79 GFLOPS | Progress: (16/20) | 15.31 s
[Task 23/25] Current/Best: 7.94/ 21.79 GFLOPS | Progress: (20/20) | 19.48 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.23/ 8.23 GFLOPS | Progress: (4/20) | 11.81 s
[Task 24/25] Current/Best: 2.15/ 8.23 GFLOPS | Progress: (8/20) | 22.87 s
[Task 24/25] Current/Best: 4.07/ 8.23 GFLOPS | Progress: (12/20) | 34.42 s Done.
+
[Task 24/25] Current/Best: 6.03/ 8.58 GFLOPS | Progress: (16/20) | 39.69 s
[Task 24/25] Current/Best: 3.42/ 8.81 GFLOPS | Progress: (20/20) | 45.70 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.74 GFLOPS | Progress: (4/20) | 11.60 s
[Task 25/25] Current/Best: 6.06/ 8.55 GFLOPS | Progress: (8/20) | 22.84 s
[Task 25/25] Current/Best: 6.07/ 8.55 GFLOPS | Progress: (12/20) | 34.25 s
[Task 25/25] Current/Best: 5.90/ 8.68 GFLOPS | Progress: (16/20) | 35.97 s
[Task 25/25] Current/Best: 2.87/ 8.92 GFLOPS | Progress: (20/20) | 46.69 s
@@ -690,8 +690,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621105
- class='n02123159 tiger cat' with probability=0.356377
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 413.13507629001833, 'median': 413.24554720004016, 'std': 0.6239807331268357}
- unoptimized: {'mean': 498.8148181299857, 'median': 498.6909075999847, 'std': 0.5668175327660779}
+ optimized: {'mean': 411.38670530000127, 'median': 411.50271740000335, 'std': 0.9684986889501206}
+ unoptimized: {'mean': 490.990710279998, 'median': 490.65708260000065, 'std': 1.161852073224186}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 23.303 seconds)
+ **Total running time of the script:** ( 10 minutes 11.264 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 f826aca42..fa92d352e 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.29e-07 secs/op
+ 1.273e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 80a6b5892..f85e2f484 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x51974e0)), stage(b, placeholder(b, 0xde68f30)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
+ [stage(a, placeholder(a, 0xd32e000)), stage(b, placeholder(b, 0x207f2900)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index c4f9e7524..40ac88a83 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**13:25.932** total execution time for **tutorial** files:
+**13:07.638** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:23.303 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:11.264 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:06.084 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.210 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.088 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:56.958 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.059 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.278 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.989 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.128 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.705 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.956 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.534 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.695 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.162 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.141 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 470a6fbe7..c2cce5f65 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,8 +301,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000006
+ Numpy running time: 0.000009
+ naive: 0.000007
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.846030002838234e-06 1.0
- naive 5.8141e-06 0.7410244413922454
- parallel 6.0488000000000004e-06 0.7709376586390696
- vector 2.4599799999999998e-05 3.1353181151615823
+ numpy 9.040690001711482e-06 1.0
+ naive 6.5863e-06 0.7285174028479193
+ parallel 5.9802e-06 0.6614760597772842
+ vector 2.4505399999999997e-05 2.7105674451132504
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018652
+ Numpy running time: 0.017712
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.340837
+ none: 3.522438
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.306062
+ blocking: 0.299239
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.343509
+ vectorization: 0.338820
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.115733
+ loop permutation: 0.113374
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.107636
+ array packing: 0.108540
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.110511
+ block caching: 0.110893
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.146145
+ parallelization: 0.146482
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3408365571000003 1.0
- blocking 0.3060615234 0.09161224087708003
- vectorization 0.34350862550000005 0.10282114064214543
- loop permutation 0.1157327619 0.034641850902296566
- array packing 0.10763585599999999 0.03221823461289973
- block caching 0.11051089239999998 0.03307880840957048
- parallelization 0.1461449957 0.043745030085177404
+ none 3.5224381027 1.0
+ blocking 0.2992390717 0.08495225834362538
+ vectorization 0.33881955480000003 0.09618893076936964
+ loop permutation 0.1133744305 0.032186351383462736
+ array packing 0.1085400648 0.03081390265362008
+ block caching 0.110893463 0.03148201892177993
+ parallelization 0.1464820248 0.04158540775712124
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.088 seconds)
+ **Total running time of the script:** ( 1 minutes 2.210 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index b45d7a237..f2b4a0037 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-9aac161a46e5aca4c433ccb901c1bb84e6c8bd0c
+40bdea8d7ae1109e33ac64265b4819bb8ebef8b3
diff --git a/docs/genindex.html b/docs/genindex.html
index 66747182f..7c733a8a6 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -4147,8 +4147,6 @@
<li><a href="reference/api/python/contrib.html#module-tvm.contrib.nnpack">module</a>
</li>
</ul></li>
- </ul></td>
- <td style="width: 33%; vertical-align: top;"><ul>
<li>
tvm.contrib.nvcc
@@ -4156,6 +4154,8 @@
<li><a href="reference/api/python/contrib.html#module-tvm.contrib.nvcc">module</a>
</li>
</ul></li>
+ </ul></td>
+ <td style="width: 33%; vertical-align: top;"><ul>
<li>
tvm.contrib.pickle_memoize
@@ -4528,12 +4528,22 @@
</li>
</ul></li>
<li><a href="reference/api/python/tir.html#tvm.tir.tvm_access_ptr">tvm_access_ptr() (in module tvm.tir)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.tvm_bmma_sync">tvm_bmma_sync() (in module tvm.tir)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.tvm_fill_fragment">tvm_fill_fragment() (in module tvm.tir)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.tvm_load_matrix_sync">tvm_load_matrix_sync() (in module tvm.tir)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.tvm_mma_sync">tvm_mma_sync() (in module tvm.tir)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.tvm_stack_alloca">tvm_stack_alloca() (in module tvm.tir)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.tvm_stack_make_array">tvm_stack_make_array() (in module tvm.tir)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.tvm_stack_make_shape">tvm_stack_make_shape() (in module tvm.tir)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.tvm_store_matrix_sync">tvm_store_matrix_sync() (in module tvm.tir)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.tvm_struct_get">tvm_struct_get() (in module tvm.tir)</a>
</li>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 0296529db..352eea76b 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.447 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.536 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 0db7ea4a9..ad4a0b20f 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa9609e41-0c3b-4baf-8ae1-e251c31d7545 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.zip7ae95aaa-5e7d-4c63-8e08-47bfe20c581d 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 46b15edd3..609dd2b14 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,14 +432,11 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 43.3MB/s]
- 25%|##5 | 10.5M/41.5M [00:00<00:00, 39.4MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 31.6MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 27.8MB/s]
- 61%|###### | 25.1M/41.5M [00:00<00:00, 27.2MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 36.7MB/s]
- 90%|########9 | 37.2M/41.5M [00:01<00:00, 37.8MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 36.5MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 47.7MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 34.5MB/s]
+ 54%|#####4 | 22.5M/41.5M [00:00<00:00, 48.6MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 55.9MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 59.2MB/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 ab8d96277..00115b0c2 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 41%|#### | 18.1M/44.7M [00:00<00:00, 190MB/s]
- 86%|########6 | 38.5M/44.7M [00:00<00:00, 204MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 211MB/s]
+ 32%|###1 | 14.2M/44.7M [00:00<00:00, 149MB/s]
+ 83%|########3 | 37.2M/44.7M [00:00<00:00, 203MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 204MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 7d7956abe..96a7ddb3a 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,6 @@ 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 5.397 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 1ef3b35b8..61f153ebb 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:09.102</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>04:51.864</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,43 +336,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:05.447</p></td>
+<td><p>01:00.536</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:05.397</p></td>
+<td><p>00:59.356</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:38.937</p></td>
+<td><p>00:37.734</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>00:28.200</p></td>
+<td><p>00:27.212</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.751</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:24.624</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:25.124</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:24.208</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.269</p></td>
+<td><p>00:22.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.705</p></td>
+<td><p>00:18.564</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:15.764</p></td>
+<td><p>00:15.341</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>00:02.506</p></td>
+<td><p>00:02.269</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index e93667968..bef6995c0 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4429 16.0607 20.0315 15.9354 1.1987
+ 16.9002 17.1537 17.4191 16.2652 0.5079
</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 750cd5446..b8aa7fd05 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,43 +436,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|2 | 3.81M/170M [00:00<00:04, 39.1MB/s]
- 4%|4 | 7.55M/170M [00:00<00:04, 38.6MB/s]
- 7%|6 | 11.2M/170M [00:00<00:04, 37.0MB/s]
- 9%|8 | 15.0M/170M [00:00<00:04, 37.9MB/s]
- 11%|#1 | 19.2M/170M [00:00<00:03, 39.8MB/s]
- 15%|#4 | 24.9M/170M [00:00<00:03, 46.5MB/s]
- 17%|#7 | 29.4M/170M [00:00<00:03, 40.1MB/s]
- 21%|## | 35.1M/170M [00:00<00:03, 45.5MB/s]
- 24%|##4 | 41.1M/170M [00:00<00:02, 50.4MB/s]
- 27%|##7 | 46.1M/170M [00:01<00:02, 43.4MB/s]
- 30%|##9 | 50.5M/170M [00:01<00:02, 44.2MB/s]
- 32%|###2 | 54.9M/170M [00:01<00:02, 41.8MB/s]
- 35%|###4 | 59.0M/170M [00:01<00:02, 41.6MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:02, 44.5MB/s]
- 40%|#### | 68.8M/170M [00:01<00:02, 46.0MB/s]
- 43%|####3 | 73.2M/170M [00:01<00:03, 33.6MB/s]
- 46%|####5 | 77.9M/170M [00:01<00:02, 37.2MB/s]
- 49%|####8 | 83.1M/170M [00:02<00:02, 41.2MB/s]
- 51%|#####1 | 87.4M/170M [00:02<00:02, 36.7MB/s]
- 54%|#####3 | 91.2M/170M [00:02<00:02, 35.1MB/s]
- 56%|#####6 | 95.2M/170M [00:02<00:02, 36.6MB/s]
- 60%|#####9 | 101M/170M [00:02<00:01, 43.8MB/s]
- 63%|######2 | 107M/170M [00:02<00:01, 46.9MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 47.8MB/s]
- 70%|######9 | 119M/170M [00:02<00:00, 55.2MB/s]
- 73%|#######3 | 124M/170M [00:03<00:01, 39.9MB/s]
- 76%|#######5 | 129M/170M [00:03<00:01, 38.7MB/s]
- 78%|#######8 | 133M/170M [00:03<00:00, 40.3MB/s]
- 81%|######## | 137M/170M [00:03<00:00, 38.4MB/s]
- 83%|########3 | 141M/170M [00:03<00:00, 39.7MB/s]
- 86%|########5 | 145M/170M [00:03<00:00, 38.0MB/s]
- 88%|########7 | 149M/170M [00:03<00:00, 38.7MB/s]
- 91%|######### | 154M/170M [00:03<00:00, 40.6MB/s]
- 93%|#########3| 159M/170M [00:04<00:00, 42.7MB/s]
- 97%|#########6| 164M/170M [00:04<00:00, 46.3MB/s]
-100%|#########9| 169M/170M [00:04<00:00, 49.0MB/s]
-100%|##########| 170M/170M [00:04<00:00, 41.9MB/s]
+ 3%|2 | 4.90M/170M [00:00<00:03, 50.6MB/s]
+ 6%|6 | 10.6M/170M [00:00<00:02, 55.7MB/s]
+ 22%|##2 | 38.2M/170M [00:00<00:00, 162MB/s]
+ 41%|#### | 69.0M/170M [00:00<00:00, 226MB/s]
+ 59%|#####8 | 100M/170M [00:00<00:00, 261MB/s]
+ 77%|#######7 | 131M/170M [00:00<00:00, 282MB/s]
+ 95%|#########5| 162M/170M [00:00<00:00, 296MB/s]
+100%|##########| 170M/170M [00:00<00:00, 245MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -567,7 +538,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 1.509 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 52.223 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 d5a7e11f0..a0f71cc1e 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 199MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 177MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +569,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2475 90.1283 94.0255 90.0310 0.4926
+ 90.0721 89.9915 91.6761 89.7874 0.2876
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.233 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.798 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 d8cc8fc11..edf275521 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.2929 121.1734 126.1004 120.5293 0.6617
+ 122.4077 122.2522 125.8146 120.5202 1.1006
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 54.234 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 55.538 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 dc4621d2d..cd51922f8 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 51.377 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.194 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 bf8b5bea3..62d1112d0 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,24 +441,23 @@ 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]
- 4%|3 | 5226/132723 [00:00<00:02, 52255.69KB/s]
- 10%|# | 13337/132723 [00:00<00:01, 69225.95KB/s]
- 15%|#5 | 20260/132723 [00:00<00:01, 56562.57KB/s]
- 21%|##1 | 28387/132723 [00:00<00:01, 65150.94KB/s]
- 26%|##6 | 35156/132723 [00:00<00:01, 49162.78KB/s]
- 33%|###2 | 43298/132723 [00:00<00:01, 57579.64KB/s]
- 37%|###7 | 49716/132723 [00:01<00:02, 35441.95KB/s]
- 43%|####3 | 57732/132723 [00:01<00:01, 43846.61KB/s]
- 50%|####9 | 65875/132723 [00:01<00:01, 51803.55KB/s]
- 56%|#####5 | 73934/132723 [00:01<00:01, 58487.45KB/s]
- 62%|######1 | 81905/132723 [00:01<00:01, 46137.54KB/s]
- 67%|######7 | 89538/132723 [00:01<00:00, 52318.01KB/s]
- 74%|#######3 | 97729/132723 [00:01<00:00, 59012.23KB/s]
- 79%|#######8 | 104670/132723 [00:02<00:00, 53507.85KB/s]
- 85%|########5 | 112834/132723 [00:02<00:00, 60054.17KB/s]
- 91%|#########1| 121004/132723 [00:02<00:00, 65449.27KB/s]
- 97%|#########7| 129196/132723 [00:02<00:00, 69769.90KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 56226.10KB/s]
+ 5%|4 | 6436/132723 [00:00<00:01, 64343.65KB/s]
+ 11%|#1 | 14793/132723 [00:00<00:01, 75648.52KB/s]
+ 17%|#7 | 23032/132723 [00:00<00:01, 78724.03KB/s]
+ 24%|##3 | 31426/132723 [00:00<00:01, 80781.45KB/s]
+ 30%|##9 | 39505/132723 [00:00<00:01, 79678.83KB/s]
+ 36%|###6 | 47848/132723 [00:00<00:01, 80939.51KB/s]
+ 42%|####2 | 56198/132723 [00:00<00:00, 81767.65KB/s]
+ 49%|####8 | 64625/132723 [00:00<00:00, 82559.17KB/s]
+ 55%|#####4 | 72973/132723 [00:00<00:00, 82844.18KB/s]
+ 61%|######1 | 81335/132723 [00:01<00:00, 83081.40KB/s]
+ 68%|######7 | 89645/132723 [00:01<00:00, 82979.06KB/s]
+ 74%|#######3 | 98017/132723 [00:01<00:00, 83202.55KB/s]
+ 80%|######## | 106393/132723 [00:01<00:00, 83367.31KB/s]
+ 86%|########6 | 114731/132723 [00:01<00:00, 83302.84KB/s]
+ 93%|#########2| 123062/132723 [00:01<00:00, 83205.34KB/s]
+ 99%|#########8| 131383/132723 [00:01<00:00, 82786.21KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 81670.83KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -501,7 +500,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 37.315 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 34.222 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 f50d0ec6c..9fffeca67 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:48.706</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:58.442</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,39 +336,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:01.509</p></td>
+<td><p>02:52.223</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:37.315</p></td>
+<td><p>02:34.222</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:54.234</p></td>
+<td><p>01:55.538</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>01:51.377</p></td>
+<td><p>01:16.194</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>01:09.233</p></td>
+<td><p>01:07.798</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:30.265</p></td>
+<td><p>00:28.737</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.557</p></td>
+<td><p>00:22.065</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.210</p></td>
+<td><p>00:21.660</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 364e08c37..2f34fb82b 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipdf73784f-d32a-4c12-a6c5-0dfa4270b97d 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.zipc8243717-03d3-494e-91ab-269d34466cd3 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 6dda9f7d6..de47c445c 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.102</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.654</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.021</p></td>
+<td><p>00:37.566</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>00:02.173</p></td>
+<td><p>00:02.163</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.900</p></td>
+<td><p>00:00.917</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index d1f202818..5112321c0 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6785us [6785us] (46.74%; 46.74%)
-FoldScaleAxis: 7732us [5us] (53.26%; 53.26%)
- FoldConstant: 7726us [1569us] (53.23%; 99.93%)
- InferType: 6158us [6158us] (42.42%; 79.70%)
+InferType: 6702us [6702us] (45.60%; 45.60%)
+FoldScaleAxis: 7995us [5us] (54.40%; 54.40%)
+ FoldConstant: 7989us [1665us] (54.36%; 99.94%)
+ InferType: 6325us [6325us] (43.03%; 79.16%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6178us [6178us] (44.79%; 44.79%)
-FoldScaleAxis: 7617us [4us] (55.21%; 55.21%)
- FoldConstant: 7613us [1540us] (55.18%; 99.94%)
- InferType: 6073us [6073us] (44.02%; 79.77%)
+InferType: 6348us [6348us] (43.21%; 43.21%)
+FoldScaleAxis: 8344us [4us] (56.79%; 56.79%)
+ FoldConstant: 8339us [1659us] (56.76%; 99.95%)
+ InferType: 6680us [6680us] (45.47%; 80.10%)
</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 56edcaecd..cf6f224c8 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.166159 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 44.074540 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 e6462a4a9..a9025d1b7 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.809425 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.919541 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 7e04550a6..be939b8c6 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018610
-Baseline: 3.349917
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017816
+Baseline: 3.257012
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.304482
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.295409
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336753
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.330258
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118981
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114631
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110009
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109573
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111204
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111509
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147611
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146465
</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 f75eca634..389a799ad 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.571</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:33.844</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.195</p></td>
+<td><p>00:31.663</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>00:01.293</p></td>
+<td><p>00:01.187</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>00:01.084</p></td>
+<td><p>00:00.995</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 7e7804278..3db7deff5 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:10.011</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:18.775</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:26.499</p></td>
+<td><p>03:34.078</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:21.581</p></td>
+<td><p>01:21.825</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:45.941</p></td>
+<td><p>00:46.323</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:18.910</p></td>
+<td><p>00:19.386</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.648</p></td>
+<td><p>00:08.683</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.432</p></td>
+<td><p>00:08.481</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 cbc4778d8..a3fb05610 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
@@ -492,216 +492,84 @@ cooperative fetching, unrolling and operator fusion.</p>
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[12] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[6] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[(threadIdx.x_2*3)] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 2)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 336)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 337)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 338)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 672)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 673)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 674)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 1008)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 64512)]
- kernel.shared_1[((threadIdx.x_2*3) + 1009)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 64513)]
- kernel.shared_1[((threadIdx.x_2*3) + 1010)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 64514)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 1344)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1345)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 1346)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- kernel.shared_1[((threadIdx.x_2*3) + 1680)] = kernel[((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*3) + 1681)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*3) + 1682)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*3) + 2016)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 129024)]
- kernel.shared_1[((threadIdx.x_2*3) + 2017)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 129025)]
- kernel.shared_1[((threadIdx.x_2*3) + 2018)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 129026)]
- }
- for (rc.outer.inner: int32, 0, 8) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*81) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*81) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 75)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 78)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 73)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 76)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 79)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 74)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 77)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*9)) + 80)]))
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (ry.outer.outer*7)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_1) + floormod(threadIdx.x_1, 9)) - 8)], 0f3 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_1) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_1) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[(threadIdx.x_2*8)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv((floormod(threadIdx.x_2, 3)*8), 3)*9)) + (ry.outer.outer*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 1)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 1), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 2)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 2), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 3)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv((floormod(threadIdx.x_2, 3)*8), 3)*9)) + (ry.outer.outer*3)) + floormod((threadIdx.x_2*2), 3)) + 9)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 4)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 4), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 5)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 5), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 6)] = kernel[(((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv((floormod(threadIdx.x_2, 3)*8), 3)*9)) + (ry.outer.outer*3)) + floormod((threadIdx.x_2*2), 3)) + 18)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*8) + 7)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*72)) + (floordiv(((floormod(threadIdx.x_2, 3)*8) + 7), 3)*9)) + (ry.outer.outer*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ }
+ for (rc.outer.inner: int32, 0, 8) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*63) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.outer.inner*3)) + 2)]))
+ }
}
}
}
- for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
}
@@ -738,7 +606,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.265 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.308 ms
</pre></div>
</div>
</div>
@@ -767,36 +635,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=16)
+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=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_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)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+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=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
-compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_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)
@@ -814,16 +682,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=8)
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=112)
+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=224)
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=112)
+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=224)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -841,195 +709,77 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[2304];
+extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[504];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 88) {
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((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 * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 3)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 336)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 337)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 338)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 672)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 673)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 674)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1008)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 64512)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1009)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 64513)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1010)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 64514)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1344)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1345)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1346)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1680)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 3) + 1681)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 3) + 1682)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + 2)];
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 3) + 2016)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 129024)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2017)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 129025)];
- kernel_shared[((((int)threadIdx.x) * 3) + 2018)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 129026)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 75)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 78)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 73)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 76)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 79)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 74)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 77)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 9)) + 80)]));
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 56) {
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[(((int)threadIdx.x) * 8)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) % 3) * 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 1)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 1) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 2)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 2) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 3)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) % 3) * 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 2) % 3)) + 9)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 4)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 4) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 5)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 5) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 6)] = kernel[(((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) % 3) * 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) * 2) % 3)) + 18)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 8) + 7)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) % 3) * 8) + 7) / 3) * 9)) + (ry_outer_outer * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_outer_inner * 3)) + 2)]));
+ }
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
</pre></div>
@@ -1064,9 +814,10 @@ In the example below we resume the status and do more 5 trials.</p>
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
Get devices for measurement successfully!
+.T
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 26.499 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 34.078 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 809c00072..cdac7c1be 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7426 9.7360 9.7819 9.7099 0.0298
+ 9.7892 9.7801 9.8291 9.7584 0.0296
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 278d7e271..a3d4d25a2 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 751.4613 751.3206 752.2142 750.8493 0.5660
+ 748.4140 748.0205 749.2736 747.9480 0.6085
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.581 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.825 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 4670d2d4f..cf6f9799a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,16 +625,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_1: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.outer.inner*128) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [256], [])[cse_var_1] = 0f32
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
compute_5[(cse_var_1 + 2)] = 0f32
compute_5[(cse_var_1 + 3)] = 0f32
@@ -650,193 +648,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 13)] = 0f32
compute_5[(cse_var_1 + 14)] = 0f32
compute_5[(cse_var_1 + 15)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 64)] = 0f32
- compute_5[(cse_var_1 + 65)] = 0f32
- compute_5[(cse_var_1 + 66)] = 0f32
- compute_5[(cse_var_1 + 67)] = 0f32
- compute_5[(cse_var_1 + 68)] = 0f32
- compute_5[(cse_var_1 + 69)] = 0f32
- compute_5[(cse_var_1 + 70)] = 0f32
- compute_5[(cse_var_1 + 71)] = 0f32
- compute_5[(cse_var_1 + 72)] = 0f32
- compute_5[(cse_var_1 + 73)] = 0f32
- compute_5[(cse_var_1 + 74)] = 0f32
- compute_5[(cse_var_1 + 75)] = 0f32
- compute_5[(cse_var_1 + 76)] = 0f32
- compute_5[(cse_var_1 + 77)] = 0f32
- compute_5[(cse_var_1 + 78)] = 0f32
- compute_5[(cse_var_1 + 79)] = 0f32
- compute_5[(cse_var_1 + 96)] = 0f32
- compute_5[(cse_var_1 + 97)] = 0f32
- compute_5[(cse_var_1 + 98)] = 0f32
- compute_5[(cse_var_1 + 99)] = 0f32
- compute_5[(cse_var_1 + 100)] = 0f32
- compute_5[(cse_var_1 + 101)] = 0f32
- compute_5[(cse_var_1 + 102)] = 0f32
- compute_5[(cse_var_1 + 103)] = 0f32
- compute_5[(cse_var_1 + 104)] = 0f32
- compute_5[(cse_var_1 + 105)] = 0f32
- compute_5[(cse_var_1 + 106)] = 0f32
- compute_5[(cse_var_1 + 107)] = 0f32
- compute_5[(cse_var_1 + 108)] = 0f32
- compute_5[(cse_var_1 + 109)] = 0f32
- compute_5[(cse_var_1 + 110)] = 0f32
- compute_5[(cse_var_1 + 111)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_67: int32 = (elem_idx*16)
- let cse_var_66: int32 = (cse_var_1 + 99)
- let cse_var_65: int32 = (cse_var_1 + 98)
- let cse_var_64: int32 = (cse_var_1 + 97)
- let cse_var_63: int32 = (cse_var_1 + 96)
- let cse_var_62: int32 = (cse_var_1 + 9)
- let cse_var_61: int32 = (cse_var_1 + 8)
- let cse_var_60: int32 = (cse_var_1 + 79)
- let cse_var_59: int32 = (cse_var_1 + 78)
- let cse_var_58: int32 = (cse_var_1 + 77)
- let cse_var_57: int32 = (cse_var_1 + 76)
- let cse_var_56: int32 = (cse_var_1 + 75)
- let cse_var_55: int32 = (cse_var_1 + 74)
- let cse_var_54: int32 = (cse_var_1 + 73)
- let cse_var_53: int32 = (cse_var_1 + 72)
- let cse_var_52: int32 = (cse_var_1 + 71)
- let cse_var_51: int32 = (cse_var_1 + 70)
- let cse_var_50: int32 = (cse_var_1 + 7)
- let cse_var_49: int32 = (cse_var_1 + 69)
- let cse_var_48: int32 = (cse_var_1 + 68)
- let cse_var_47: int32 = (cse_var_1 + 67)
- let cse_var_46: int32 = (cse_var_1 + 66)
- let cse_var_45: int32 = (cse_var_1 + 65)
- let cse_var_44: int32 = (cse_var_1 + 64)
- let cse_var_43: int32 = (cse_var_1 + 6)
- let cse_var_42: int32 = (cse_var_1 + 5)
- let cse_var_41: int32 = (cse_var_1 + 47)
- let cse_var_40: int32 = (cse_var_1 + 46)
- let cse_var_39: int32 = (cse_var_1 + 45)
- let cse_var_38: int32 = (cse_var_1 + 44)
- let cse_var_37: int32 = (cse_var_1 + 43)
- let cse_var_36: int32 = (cse_var_1 + 42)
- let cse_var_35: int32 = (cse_var_1 + 41)
- let cse_var_34: int32 = (cse_var_1 + 40)
- let cse_var_33: int32 = (cse_var_1 + 4)
- let cse_var_32: int32 = (cse_var_1 + 39)
- let cse_var_31: int32 = (cse_var_1 + 38)
- let cse_var_30: int32 = (cse_var_1 + 37)
- let cse_var_29: int32 = (cse_var_1 + 36)
- let cse_var_28: int32 = (cse_var_1 + 35)
- let cse_var_27: int32 = (cse_var_1 + 34)
- let cse_var_26: int32 = (cse_var_1 + 33)
- let cse_var_25: int32 = (cse_var_1 + 32)
- let cse_var_24: int32 = (cse_var_1 + 3)
- let cse_var_23: int32 = (cse_var_1 + 2)
- let cse_var_22: int32 = (cse_var_1 + 15)
- let cse_var_21: int32 = (cse_var_1 + 14)
- let cse_var_20: int32 = (cse_var_1 + 13)
- let cse_var_19: int32 = (cse_var_1 + 12)
- let cse_var_18: int32 = (cse_var_1 + 111)
- let cse_var_17: int32 = (cse_var_1 + 110)
- let cse_var_16: int32 = (cse_var_1 + 11)
- let cse_var_15: int32 = (cse_var_1 + 109)
- let cse_var_14: int32 = (cse_var_1 + 108)
- let cse_var_13: int32 = (cse_var_1 + 107)
- let cse_var_12: int32 = (cse_var_1 + 106)
- let cse_var_11: int32 = (cse_var_1 + 105)
- let cse_var_10: int32 = (cse_var_1 + 104)
- let cse_var_9: int32 = (cse_var_1 + 103)
- let cse_var_8: int32 = (cse_var_1 + 102)
- let cse_var_7: int32 = (cse_var_1 + 101)
- let cse_var_6: int32 = (cse_var_1 + 100)
- let cse_var_5: int32 = (cse_var_1 + 10)
- let cse_var_4: int32 = (cse_var_1 + 1)
- let cse_var_3: int32 = ((i0.outer*2048) + (i.outer.inner*1024))
- {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_67)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- }
+ }
+ }
+ for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
+ for (i.inner: int32, 0, 8) {
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_2: int32 = ((i.outer.inner*128) + (i.inner*16))
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + 1)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_4: int32 = (((i.outer.inner*128) + (i.inner*16)) + 2)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*128) + (i.inner*16)) + 3)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*128) + (i.inner*16)) + 4)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*128) + (i.inner*16)) + 5)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*128) + (i.inner*16)) + 6)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*128) + (i.inner*16)) + 7)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*128) + (i.inner*16)) + 8)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*128) + (i.inner*16)) + 9)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*128) + (i.inner*16)) + 10)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*128) + (i.inner*16)) + 11)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*128) + (i.inner*16)) + 12)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*128) + (i.inner*16)) + 13)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*128) + (i.inner*16)) + 14)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*128) + (i.inner*16)) + 15)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_68: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*32))
- compute[ramp(cse_var_68, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+ compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -874,7 +759,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.019 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.844 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 72c47d426..ef1130294 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.845</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.368</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.809</p></td>
+<td><p>00:45.334</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>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index d31f526b7..c4496bee6 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 194.69/194.69 result: MeasureResult(costs=(0.0011890512222222224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0911288261413574, timestamp=1661412805.2547846) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/194.69 result: Traceback (most recent call last):
+No: 9 GFLOPS: 174.77/174.77 result: MeasureResult(costs=(0.0013245948555555556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0623905658721924, timestamp=1661426185.0137548) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/174.77 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 259.81/259.81 result: MeasureResult(costs=(0.0008910316574585634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7313928604125977, timestamp=1661412806.162532) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+No: 11 GFLOPS: 259.92/259.92 result: MeasureResult(costs=(0.0008906486243093922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7344768047332764, timestamp=1661426185.9444644) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.29/259.81 result: MeasureResult(costs=(0.043743752000000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8454883098602295, timestamp=1661412810.7189252) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.34/259.81 result: MeasureResult(costs=(0.069390816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.541620492935181, timestamp=1661412811.9708114) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.30/259.92 result: MeasureResult(costs=(0.043681782499999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7933611869812012, timestamp=1661426190.4473178) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/259.92 result: MeasureResult(costs=(0.06939374050000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.509384632110596, timestamp=1661426191.688685) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.03/259.81 result: MeasureResult(costs=(0.008257752857142859,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.258805513381958, timestamp=1661412823.0187645) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+No: 18 GFLOPS: 27.93/259.92 result: MeasureResult(costs=(0.008289639357142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2552039623260498, timestamp=1661426202.725381) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/259.81 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/259.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001277
+Time cost of this operator: 0.001272
</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 6ed77156c..164d8890b 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.1 98.725 (1, 2, 10, 10, 3) 2 1 [309.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.024 0.966 (1, 6, 10, 10) 1 1 [3.024]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.309 (1, 1, 10, 10, 3) 1 1 [0.968]
-Total_time - 313.092 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.4 98.732 (1, 2, 10, 10, 3) 2 1 [313.4]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.064 0.965 (1, 6, 10, 10) 1 1 [3.064]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.303 (1, 1, 10, 10, 3) 1 1 [0.961]
+Total_time - 317.425 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 120.6 97.797 (1, 6, 10, 10, 1) 2 1 [120.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.744 1.414 (1, 6, 10, 10) 1 1 [1.744]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.789 (1, 1, 10, 10, 3) 1 1 [0.973]
-Total_time - 123.317 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 130.1 97.938 (1, 6, 10, 10, 1) 2 1 [130.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.786 1.345 (1, 6, 10, 10) 1 1 [1.786]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.718 (1, 1, 10, 10, 3) 1 1 [0.953]
+Total_time - 132.84 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 9d5248ec4..cbf5ff2a2 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpxxco06av/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpknjo1lwr/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpxxco06av/images/target contains 8144 images
-/tmp/tmpxxco06av/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpknjo1lwr/images/target contains 8144 images
+/tmp/tmpknjo1lwr/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2094 - accuracy: 0.9294 - val_loss: 0.1389 - val_accuracy: 0.9577
+328/328 - 55s - loss: 0.2134 - accuracy: 0.9251 - val_loss: 0.1621 - val_accuracy: 0.9569
Epoch 2/3
-328/328 - 52s - loss: 0.0934 - accuracy: 0.9656 - val_loss: 0.1387 - val_accuracy: 0.9532
+328/328 - 52s - loss: 0.1061 - accuracy: 0.9599 - val_loss: 0.1173 - val_accuracy: 0.9637
Epoch 3/3
-328/328 - 52s - loss: 0.0687 - accuracy: 0.9742 - val_loss: 0.1056 - val_accuracy: 0.9694
+328/328 - 52s - loss: 0.0704 - accuracy: 0.9745 - val_loss: 0.1219 - val_accuracy: 0.9569
-<keras.callbacks.History object at 0x7f20286e0790>
+<keras.callbacks.History object at 0x7f6df5c2e810>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 16.243 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 28.979 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 f47ce8d53..08efb4fc3 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:08.954</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:20.896</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:16.243</p></td>
+<td><p>04:28.979</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:41.884</p></td>
+<td><p>00:41.408</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.544</p></td>
+<td><p>00:07.290</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.282</p></td>
+<td><p>00:03.217</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index c3e2e1e71..97167e38b 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:38.376</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:42.776</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.015</p></td>
+<td><p>00:31.380</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>00:04.917</p></td>
+<td><p>00:09.968</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>00:01.437</p></td>
+<td><p>00:01.420</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 0fcb8f215..8ac2c35a2 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f1f9384e440>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f6d7fe81200>
</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 3db24243e..1694867f2 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.499</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.028</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:02.055</p></td>
+<td><p>00:01.859</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>00:01.129</p></td>
+<td><p>00:00.958</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>00:00.572</p></td>
+<td><p>00:00.524</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>00:00.556</p></td>
+<td><p>00:00.506</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.103</p></td>
+<td><p>00:00.099</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.042</p></td>
+<td><p>00:00.041</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 4cd0a639e..66f4a2b78 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpx6do_wif/input0.cc'\nsource_filename = \"/tmp/tmpx6do_wif/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp8das6brp/input0.cc'\nsource_filename = \"/tmp/tmp8das6brp/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/objects.inv b/docs/objects.inv
index 4395adf37..20878cda3 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 451a81b6d..2ee45f6ac 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index 8520dd1bb..600a7fc96 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -705,202 +705,217 @@
<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.tvm_throw_last_error" title="tvm.tir.tvm_throw_last_error"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tvm_throw_last_error</span></code></a>()</p></td>
<td><p>Throw TVMGetLastError()</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.vectorlow" title="tvm.tir.vectorlow"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorlow</span></code></a>(dtype, vec)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.tvm_load_matrix_sync" title="tvm.tir.tvm_load_matrix_sync"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tvm_load_matrix_sync</span></code></a>(fragment, m, n, k, ...)</p></td>
+<td><p>TVM intrinsic for tensor core load operators</p></td>
+</tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.tvm_store_matrix_sync" title="tvm.tir.tvm_store_matrix_sync"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tvm_store_matrix_sync</span></code></a>(fragment, m, n, k, ...)</p></td>
+<td><p>TVM intrinsic for tensor core store operators</p></td>
+</tr>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.tvm_mma_sync" title="tvm.tir.tvm_mma_sync"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tvm_mma_sync</span></code></a>(fragment_d, index_d, ...)</p></td>
+<td><p>TVM intrinsic for tensor core mma_sync operators</p></td>
+</tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.tvm_bmma_sync" title="tvm.tir.tvm_bmma_sync"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tvm_bmma_sync</span></code></a>(fragment_d, index_d, ...)</p></td>
+<td><p>TVM intrinsic for tensor core bmma_sync operators</p></td>
+</tr>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.tvm_fill_fragment" title="tvm.tir.tvm_fill_fragment"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tvm_fill_fragment</span></code></a>(fragment, m, n, k, index, ...)</p></td>
+<td><p>TVM intrinsic for tensor core fill_fragment operators</p></td>
+</tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.vectorlow" title="tvm.tir.vectorlow"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorlow</span></code></a>(dtype, vec)</p></td>
<td><p>Get the low level half of the vector</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.vectorhigh" title="tvm.tir.vectorhigh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorhigh</span></code></a>(dtype, vec)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.vectorhigh" title="tvm.tir.vectorhigh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorhigh</span></code></a>(dtype, vec)</p></td>
<td><p>Get the high level half of the vector</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.vectorcombine" title="tvm.tir.vectorcombine"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorcombine</span></code></a>(dtype, vec1, vec2)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.vectorcombine" title="tvm.tir.vectorcombine"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorcombine</span></code></a>(dtype, vec1, vec2)</p></td>
<td><p>Concat two vectors</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.infinity" title="tvm.tir.infinity"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infinity</span></code></a>(dtype[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.infinity" title="tvm.tir.infinity"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infinity</span></code></a>(dtype[, span])</p></td>
<td><p>infinity value of dtype</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.reinterpret" title="tvm.tir.reinterpret"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reinterpret</span></code></a>(dtype, value)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.reinterpret" title="tvm.tir.reinterpret"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reinterpret</span></code></a>(dtype, value)</p></td>
<td><p>infinity value of dtype</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.exp" title="tvm.tir.exp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.exp" title="tvm.tir.exp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp</span></code></a>(x)</p></td>
<td><p>Take exponential of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.exp2" title="tvm.tir.exp2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp2</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.exp2" title="tvm.tir.exp2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp2</span></code></a>(x)</p></td>
<td><p>Calculate 2**x</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.exp10" title="tvm.tir.exp10"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp10</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.exp10" title="tvm.tir.exp10"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp10</span></code></a>(x)</p></td>
<td><p>Calculate 10**x</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.log" title="tvm.tir.log"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.log" title="tvm.tir.log"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log</span></code></a>(x)</p></td>
<td><p>Take log of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.log2" title="tvm.tir.log2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log2</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.log2" title="tvm.tir.log2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log2</span></code></a>(x)</p></td>
<td><p>Take log2 of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.log10" title="tvm.tir.log10"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log10</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.log10" title="tvm.tir.log10"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log10</span></code></a>(x)</p></td>
<td><p>Take log10 of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.log1p" title="tvm.tir.log1p"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log1p</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.log1p" title="tvm.tir.log1p"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log1p</span></code></a>(x)</p></td>
<td><p>Take log(x + 1) with respect to input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.ldexp" title="tvm.tir.ldexp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ldexp</span></code></a>(x1, x2)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.ldexp" title="tvm.tir.ldexp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ldexp</span></code></a>(x1, x2)</p></td>
<td><p>Returns x1 * (2 ** x2).</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.clz" title="tvm.tir.clz"><code class="xref py py-obj docutils literal notranslate"><span class="pre">clz</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.clz" title="tvm.tir.clz"><code class="xref py py-obj docutils literal notranslate"><span class="pre">clz</span></code></a>(x)</p></td>
<td><p>Count leading zero bits of an integer x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sin" title="tvm.tir.sin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sin</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sin" title="tvm.tir.sin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sin</span></code></a>(x)</p></td>
<td><p>Take sin of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sinh" title="tvm.tir.sinh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sinh</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sinh" title="tvm.tir.sinh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sinh</span></code></a>(x)</p></td>
<td><p>Take sinh of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.asin" title="tvm.tir.asin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">asin</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.asin" title="tvm.tir.asin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">asin</span></code></a>(x)</p></td>
<td><p>Take asin of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.asinh" title="tvm.tir.asinh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">asinh</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.asinh" title="tvm.tir.asinh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">asinh</span></code></a>(x)</p></td>
<td><p>Take asinh of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.cos" title="tvm.tir.cos"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cos</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.cos" title="tvm.tir.cos"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cos</span></code></a>(x)</p></td>
<td><p>Take cos of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.cosh" title="tvm.tir.cosh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cosh</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.cosh" title="tvm.tir.cosh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cosh</span></code></a>(x)</p></td>
<td><p>Take cosh of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.acos" title="tvm.tir.acos"><code class="xref py py-obj docutils literal notranslate"><span class="pre">acos</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.acos" title="tvm.tir.acos"><code class="xref py py-obj docutils literal notranslate"><span class="pre">acos</span></code></a>(x)</p></td>
<td><p>Take acos of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.acosh" title="tvm.tir.acosh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">acosh</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.acosh" title="tvm.tir.acosh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">acosh</span></code></a>(x)</p></td>
<td><p>Take acos of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.tan" title="tvm.tir.tan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tan</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.tan" title="tvm.tir.tan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tan</span></code></a>(x)</p></td>
<td><p>Take tan of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.tanh" title="tvm.tir.tanh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tanh</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.tanh" title="tvm.tir.tanh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tanh</span></code></a>(x)</p></td>
<td><p>Take hyperbolic tanh of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.atan" title="tvm.tir.atan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atan</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.atan" title="tvm.tir.atan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atan</span></code></a>(x)</p></td>
<td><p>Take atan of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.atan2" title="tvm.tir.atan2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atan2</span></code></a>(x1, x2)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.atan2" title="tvm.tir.atan2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atan2</span></code></a>(x1, x2)</p></td>
<td><p>Take arctan2(x1, x2).</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.atanh" title="tvm.tir.atanh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atanh</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.atanh" title="tvm.tir.atanh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atanh</span></code></a>(x)</p></td>
<td><p>Take atanh of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.erf" title="tvm.tir.erf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">erf</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.erf" title="tvm.tir.erf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">erf</span></code></a>(x)</p></td>
<td><p>Take gauss error function of the input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sigmoid" title="tvm.tir.sigmoid"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sigmoid</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sigmoid" title="tvm.tir.sigmoid"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sigmoid</span></code></a>(x)</p></td>
<td><p>Quick function to get sigmoid</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sqrt" title="tvm.tir.sqrt"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sqrt</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sqrt" title="tvm.tir.sqrt"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sqrt</span></code></a>(x)</p></td>
<td><p>Take square root of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.rsqrt" title="tvm.tir.rsqrt"><code class="xref py py-obj docutils literal notranslate"><span class="pre">rsqrt</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.rsqrt" title="tvm.tir.rsqrt"><code class="xref py py-obj docutils literal notranslate"><span class="pre">rsqrt</span></code></a>(x)</p></td>
<td><p>Take reciprocal of square root of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.floor" title="tvm.tir.floor"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floor</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.floor" title="tvm.tir.floor"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floor</span></code></a>(x[, span])</p></td>
<td><p>Take floor of float input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.ceil" title="tvm.tir.ceil"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ceil</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.ceil" title="tvm.tir.ceil"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ceil</span></code></a>(x[, span])</p></td>
<td><p>Take ceil of float input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.hypot" title="tvm.tir.hypot"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hypot</span></code></a>(x1, x2)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.hypot" title="tvm.tir.hypot"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hypot</span></code></a>(x1, x2)</p></td>
<td><p>Equivalent to sqrt(x1**2 + x2**2), element-wise.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.trunc" title="tvm.tir.trunc"><code class="xref py py-obj docutils literal notranslate"><span class="pre">trunc</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.trunc" title="tvm.tir.trunc"><code class="xref py py-obj docutils literal notranslate"><span class="pre">trunc</span></code></a>(x[, span])</p></td>
<td><p>Get truncated value of the input.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.abs" title="tvm.tir.abs"><code class="xref py py-obj docutils literal notranslate"><span class="pre">abs</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.abs" title="tvm.tir.abs"><code class="xref py py-obj docutils literal notranslate"><span class="pre">abs</span></code></a>(x[, span])</p></td>
<td><p>Get absolute value of the input element-wise.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.round" title="tvm.tir.round"><code class="xref py py-obj docutils literal notranslate"><span class="pre">round</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.round" title="tvm.tir.round"><code class="xref py py-obj docutils literal notranslate"><span class="pre">round</span></code></a>(x[, span])</p></td>
<td><p>Round elements of the array to the nearest integer.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.nextafter" title="tvm.tir.nextafter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">nextafter</span></code></a>(x1, x2)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.nextafter" title="tvm.tir.nextafter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">nextafter</span></code></a>(x1, x2)</p></td>
<td><p>Return the next floating-point value after x1 towards x2.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.nearbyint" title="tvm.tir.nearbyint"><code class="xref py py-obj docutils literal notranslate"><span class="pre">nearbyint</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.nearbyint" title="tvm.tir.nearbyint"><code class="xref py py-obj docutils literal notranslate"><span class="pre">nearbyint</span></code></a>(x[, span])</p></td>
<td><p>Round elements of the array to the nearest integer.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.power" title="tvm.tir.power"><code class="xref py py-obj docutils literal notranslate"><span class="pre">power</span></code></a>(x, y[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.power" title="tvm.tir.power"><code class="xref py py-obj docutils literal notranslate"><span class="pre">power</span></code></a>(x, y[, span])</p></td>
<td><p>x power y</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.popcount" title="tvm.tir.popcount"><code class="xref py py-obj docutils literal notranslate"><span class="pre">popcount</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.popcount" title="tvm.tir.popcount"><code class="xref py py-obj docutils literal notranslate"><span class="pre">popcount</span></code></a>(x)</p></td>
<td><p>Count the number of set bits in input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.fmod" title="tvm.tir.fmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">fmod</span></code></a>(x, y)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.fmod" title="tvm.tir.fmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">fmod</span></code></a>(x, y)</p></td>
<td><p>Return the remainder of x divided by y with the same sign as x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.if_then_else" title="tvm.tir.if_then_else"><code class="xref py py-obj docutils literal notranslate"><span class="pre">if_then_else</span></code></a>(cond, t, f[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.if_then_else" title="tvm.tir.if_then_else"><code class="xref py py-obj docutils literal notranslate"><span class="pre">if_then_else</span></code></a>(cond, t, f[, span])</p></td>
<td><p>Conditional selection expression.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.likely" title="tvm.tir.likely"><code class="xref py py-obj docutils literal notranslate"><span class="pre">likely</span></code></a>(cond[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.likely" title="tvm.tir.likely"><code class="xref py py-obj docutils literal notranslate"><span class="pre">likely</span></code></a>(cond[, span])</p></td>
<td><p>Mark condition as likely.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.isnan" title="tvm.tir.isnan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isnan</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.isnan" title="tvm.tir.isnan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isnan</span></code></a>(x[, span])</p></td>
<td><p>Check if input value is Nan.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.isnullptr" title="tvm.tir.isnullptr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isnullptr</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.isnullptr" title="tvm.tir.isnullptr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isnullptr</span></code></a>(x[, span])</p></td>
<td><p>Check if input value is nullptr.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.isfinite" title="tvm.tir.isfinite"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isfinite</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.isfinite" title="tvm.tir.isfinite"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isfinite</span></code></a>(x[, span])</p></td>
<td><p>Check if input value is finite.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.isinf" title="tvm.tir.isinf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isinf</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.isinf" title="tvm.tir.isinf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isinf</span></code></a>(x[, span])</p></td>
<td><p>Check if input value is infinite.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.copysign" title="tvm.tir.copysign"><code class="xref py py-obj docutils literal notranslate"><span class="pre">copysign</span></code></a>(x1, x2)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.copysign" title="tvm.tir.copysign"><code class="xref py py-obj docutils literal notranslate"><span class="pre">copysign</span></code></a>(x1, x2)</p></td>
<td><p>Change the sign of x1 to that of x2, element-wise.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.div" title="tvm.tir.div"><code class="xref py py-obj docutils literal notranslate"><span class="pre">div</span></code></a>(a, b[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.div" title="tvm.tir.div"><code class="xref py py-obj docutils literal notranslate"><span class="pre">div</span></code></a>(a, b[, span])</p></td>
<td><p>Compute a / b as in C/C++ semantics.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.indexdiv" title="tvm.tir.indexdiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">indexdiv</span></code></a>(a, b[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.indexdiv" title="tvm.tir.indexdiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">indexdiv</span></code></a>(a, b[, span])</p></td>
<td><p>Compute floor(a / b) where a and b are non-negative.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.indexmod" title="tvm.tir.indexmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">indexmod</span></code></a>(a, b[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.indexmod" title="tvm.tir.indexmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">indexmod</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the remainder of indexdiv.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.truncdiv" title="tvm.tir.truncdiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">truncdiv</span></code></a>(a, b[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.truncdiv" title="tvm.tir.truncdiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">truncdiv</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the truncdiv of two expressions.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.truncmod" title="tvm.tir.truncmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">truncmod</span></code></a>(a, b[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.truncmod" title="tvm.tir.truncmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">truncmod</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the truncmod of two expressions.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.floordiv" title="tvm.tir.floordiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floordiv</span></code></a>(a, b[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.floordiv" title="tvm.tir.floordiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floordiv</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the floordiv of two expressions.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.floormod" title="tvm.tir.floormod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floormod</span></code></a>(a, b[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.floormod" title="tvm.tir.floormod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floormod</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the floormod of two expressions.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.ceildiv" title="tvm.tir.ceildiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ceildiv</span></code></a>(lhs, rhs[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.ceildiv" title="tvm.tir.ceildiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ceildiv</span></code></a>(lhs, rhs[, span])</p></td>
<td><p>Generic ceildiv operator.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.comm_reducer" title="tvm.tir.comm_reducer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">comm_reducer</span></code></a>(fcombine, fidentity[, name])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.comm_reducer" title="tvm.tir.comm_reducer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">comm_reducer</span></code></a>(fcombine, fidentity[, name])</p></td>
<td><p>Create a commutative reducer for reduction.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.min" title="tvm.tir.min"><code class="xref py py-obj docutils literal notranslate"><span class="pre">min</span></code></a>(expr, axis[, where, init])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.min" title="tvm.tir.min"><code class="xref py py-obj docutils literal notranslate"><span class="pre">min</span></code></a>(expr, axis[, where, init])</p></td>
<td><p>Create a min expression over axis.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.max" title="tvm.tir.max"><code class="xref py py-obj docutils literal notranslate"><span class="pre">max</span></code></a>(expr, axis[, where, init])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.max" title="tvm.tir.max"><code class="xref py py-obj docutils literal notranslate"><span class="pre">max</span></code></a>(expr, axis[, where, init])</p></td>
<td><p>Create a max expression over axis.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sum" title="tvm.tir.sum"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sum</span></code></a>(expr, axis[, where, init])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sum" title="tvm.tir.sum"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sum</span></code></a>(expr, axis[, where, init])</p></td>
<td><p>Create a sum expression over axis.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.q_multiply_shift" title="tvm.tir.q_multiply_shift"><code class="xref py py-obj docutils literal notranslate"><span class="pre">q_multiply_shift</span></code></a>(x, y, q, s)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.q_multiply_shift" title="tvm.tir.q_multiply_shift"><code class="xref py py-obj docutils literal notranslate"><span class="pre">q_multiply_shift</span></code></a>(x, y, q, s)</p></td>
<td><p>Execute a multiplication between two Q-numbers x and y followed by a right shift s.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.shift_left" title="tvm.tir.shift_left"><code class="xref py py-obj docutils literal notranslate"><span class="pre">shift_left</span></code></a>(x, y[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.shift_left" title="tvm.tir.shift_left"><code class="xref py py-obj docutils literal notranslate"><span class="pre">shift_left</span></code></a>(x, y[, span])</p></td>
<td><p>Return the result of x left shifted by y bits.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.shift_right" title="tvm.tir.shift_right"><code class="xref py py-obj docutils literal notranslate"><span class="pre">shift_right</span></code></a>(x, y[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.shift_right" title="tvm.tir.shift_right"><code class="xref py py-obj docutils literal notranslate"><span class="pre">shift_right</span></code></a>(x, y[, span])</p></td>
<td><p>Return the result of x right shifted by y bits.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.TVMBackendAllocWorkspace" title="tvm.tir.TVMBackendAllocWorkspace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TVMBackendAllocWorkspace</span></code></a>(device_type, ...)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.TVMBackendAllocWorkspace" title="tvm.tir.TVMBackendAllocWorkspace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TVMBackendAllocWorkspace</span></code></a>(device_type, ...)</p></td>
<td><p>Backend function to allocate temporal workspace</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.TVMBackendFreeWorkspace" title="tvm.tir.TVMBackendFreeWorkspace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TVMBackendFreeWorkspace</span></code></a>(device_type, ...)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.TVMBackendFreeWorkspace" title="tvm.tir.TVMBackendFreeWorkspace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TVMBackendFreeWorkspace</span></code></a>(device_type, ...)</p></td>
<td><p>Backend function to free temporal workspace.</p></td>
</tr>
</tbody>
@@ -3401,6 +3416,134 @@ tvm.default_trace_action is used.</p>
</dl>
</dd></dl>
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.tvm_load_matrix_sync">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">tvm_load_matrix_sync</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fragment</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre" [...]
+<dd><p>TVM intrinsic for tensor core load operators</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>fragment</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The wmma fragment.</p></li>
+<li><p><strong>m</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>n</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>k</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>index</strong> (<em>Expr</em>) – The fragment index.</p></li>
+<li><p><strong>buffer_ptr</strong> (<em>Expr</em>) – The fragment buffer pointer.</p></li>
+<li><p><strong>stride</strong> (<em>Expr</em>) – The fragment stride.</p></li>
+<li><p><strong>layout</strong> (<em>Literal</em><em>[</em><em>"row_major"</em><em>, </em><em>"column_major"</em><em>]</em>) – The fragment layout.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.tvm_store_matrix_sync">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">tvm_store_matrix_sync</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fragment</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre [...]
+<dd><p>TVM intrinsic for tensor core store operators</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>fragment</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The wmma fragment.</p></li>
+<li><p><strong>m</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>n</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>k</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>index</strong> (<em>Expr</em>) – The fragment index.</p></li>
+<li><p><strong>buffer_ptr</strong> (<em>Expr</em>) – The fragment buffer pointer.</p></li>
+<li><p><strong>stride</strong> (<em>Expr</em>) – The fragment stride.</p></li>
+<li><p><strong>layout</strong> (<em>Literal</em><em>[</em><em>"row_major"</em><em>, </em><em>"column_major"</em><em>]</em>) – The fragment layout.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.tvm_mma_sync">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">tvm_mma_sync</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fragment_d</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">index_d</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fragment_a</span></span></em>, <em class="sig-param"><span class="n"><span cl [...]
+<dd><p>TVM intrinsic for tensor core mma_sync operators</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>fragment_d</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The wmma fragment_d.</p></li>
+<li><p><strong>index_d</strong> (<em>Expr</em>) – The fragment_d index.</p></li>
+<li><p><strong>fragment_a</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The wmma fragment_a.</p></li>
+<li><p><strong>index_a</strong> (<em>Expr</em>) – The fragment_a index.</p></li>
+<li><p><strong>fragment_b</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The wmma fragment_b.</p></li>
+<li><p><strong>index_b</strong> (<em>Expr</em>) – The fragment_b index.</p></li>
+<li><p><strong>fragment_c</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The wmma fragment_c.</p></li>
+<li><p><strong>index_c</strong> (<em>Expr</em>) – The fragment_c index.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.tvm_bmma_sync">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">tvm_bmma_sync</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fragment_d</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">index_d</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fragment_a</span></span></em>, <em class="sig-param"><span class="n"><span c [...]
+<dd><p>TVM intrinsic for tensor core bmma_sync operators</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>fragment_d</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The bwmma fragment_d.</p></li>
+<li><p><strong>index_d</strong> (<em>Expr</em>) – The fragment_d index.</p></li>
+<li><p><strong>fragment_a</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The bwmma fragment_a.</p></li>
+<li><p><strong>index_a</strong> (<em>Expr</em>) – The fragment_a index.</p></li>
+<li><p><strong>fragment_b</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The bwmma fragment_b.</p></li>
+<li><p><strong>index_b</strong> (<em>Expr</em>) – The fragment_b index.</p></li>
+<li><p><strong>fragment_c</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The bwmma fragment_c.</p></li>
+<li><p><strong>index_c</strong> (<em>Expr</em>) – The fragment_c index.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.tvm_fill_fragment">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">tvm_fill_fragment</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fragment</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k< [...]
+<dd><p>TVM intrinsic for tensor core fill_fragment operators</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>fragment</strong> (<a class="reference internal" href="#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a>) – The wmma fragment</p></li>
+<li><p><strong>m</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>n</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>k</strong> (<em>UIntImm</em>) – The shape of wmma fragment.</p></li>
+<li><p><strong>index</strong> (<em>Expr</em>) – The fragment index.</p></li>
+<li><p><strong>value</strong> (<em>Expr</em>) – The value to be filled in fragment.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
<dl class="py function">
<dt class="sig sig-object py" id="tvm.tir.vectorlow">
<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">vectorlow</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vec</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.vectorlow" title="Permalink to this definition">¶</a></dt>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index da799b178..8beb502ee 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/9aac161a4/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index f1fdfc3e8..092524bf3 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/9aac161a4/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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 309b4965f..45c98f197 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/9aac161a4/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index ea3a85d1d..b808fd4af 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/9aac161a4/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index d216f2733..c97383ad1 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/9aac161a4/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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 3801e551f..ad5afb365 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/9aac161a4/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 636d28c13..a119bad28 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 1893c3301..0097f9f5d 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 0f0ec8e6e..a7d0cfe55 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/9aac161a4/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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 6068136ea..6afa01677 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index cf85328ce..3c6bf619e 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/9aac161a4/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index b4b702a57..37561a9a4 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 9d54558b4..228fcd17e 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/9aac161a4/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index beee96b30..92d10747e 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/9aac161a4/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 3f3dca331..78159e1cc 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/9aac161a4/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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 b0a3164c9..d2f108efd 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/9aac161a4/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index d243146fc..bbb3e0abb 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/9aac161a4/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index f43f0fd22..0f44670fe 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/9aac161a4/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 61678717d..e67c87fd2 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/9aac161a4/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index f4985bf32..60301a7d5 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/9aac161a4/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 891411861..b7fce322b 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index f9de702c5..127cd6f1c 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9aac161a4/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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 959bf2bb8..ccf59fde3 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/9aac161a4/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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 36d7d1c60..d49db3cae 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/9aac161a4/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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/9aac161a4/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/40bdea8d7/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 b11040341..c6892019e 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 b0a3c8be2..2c6724ede 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.791</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.005</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:20.785</p></td>
+<td><p>00:20.999</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index b0ddbb783..7379aee73 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.10s!
+resnet18_v1 inference graph built in 22.46s!
</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 e09bf4602..1a45fb92b 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.63s!
+yolov3-tiny inference graph built in 15.92s!
</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 b18d4bfb7..c6ff52551 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:30.922</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:29.384</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.495</p></td>
+<td><p>00:47.184</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:42.426</p></td>
+<td><p>00:42.200</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 7eace159c..560703735 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.313</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.258</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.881</p></td>
+<td><p>00:02.862</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>00:00.432</p></td>
+<td><p>00:00.396</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 a5f3ad7a3..7fa6d708f 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.781</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.714</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.409</p></td>
+<td><p>00:00.384</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>00:00.372</p></td>
+<td><p>00:00.330</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 f15deacb2..18d78242e 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -565,7 +565,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.756 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.166 ms
</pre></div>
</div>
</div>
@@ -639,7 +639,6 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.084 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 da9ed22fb..db81de15b 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 9.11/9.11 result: MeasureResult(costs=(0.0294744746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6073787212371826, timestamp=1661411553.6023083) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.51/9.11 result: MeasureResult(costs=(0.10700922419999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.860762357711792, timestamp=1661411555.4756367) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.022767709400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.549781322479248, timestamp=1661411556.5442965) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.85/11.79 result: MeasureResult(costs=(0.1451199476,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4403741359710693, timestamp=1661411559.0312407) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.65/11.79 result: MeasureResult(costs=(0.0735167652,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3179419040679932, timestamp=1661411560.4768026) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.82/11.79 result: MeasureResult(costs=(0.14732233060000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4836344718933105, timestamp=1661411563.5380652) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.86/11.79 result: MeasureResult(costs=(0.3105263904,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0938615798950195, timestamp=1661411569.2138937) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.15/11.79 result: MeasureResult(costs=(0.0264373262,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5743741989135742, timestamp=1661411569.8078992) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.91/11.79 result: MeasureResult(costs=(0.1406850224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3574085235595703, timestamp=1661411572.2871306) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.77/11.79 result: MeasureResult(costs=(0.0968905154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6575357913970947, timestamp=1661411574.001657) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.77/10.77 result: MeasureResult(costs=(0.024922450399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.532639741897583, timestamp=1661425007.8455124) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.93/10.77 result: MeasureResult(costs=(0.09165923699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6069185733795166, timestamp=1661425009.4760969) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.022665557,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5586798191070557, timestamp=1661425010.5272446) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.45/11.84 result: MeasureResult(costs=(0.18519991819999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.087189197540283, timestamp=1661425014.1780627) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.46/11.84 result: MeasureResult(costs=(0.0776558006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3820717334747314, timestamp=1661425015.6873703) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.46/11.84 result: MeasureResult(costs=(0.1835167872,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1046082973480225, timestamp=1661425018.836185) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.86/11.84 result: MeasureResult(costs=(0.3104250466,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.087313890457153, timestamp=1661425024.495183) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.70/11.84 result: MeasureResult(costs=(0.025083290199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5430276393890381, timestamp=1661425025.0586967) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.74/11.84 result: MeasureResult(costs=(0.154582941,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.574871778488159, timestamp=1661425027.7539246) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.65/11.84 result: MeasureResult(costs=(0.1012859838,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.724215030670166, timestamp=1661425029.5370471) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 7d07024e9..d633dcd3f 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 498.8148181299857, 'median': 498.6909075999847, 'std': 0.5668175327660779}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 490.990710279998, 'median': 490.65708260000065, 'std': 1.161852073224186}
</pre></div>
</div>
</div>
@@ -706,178 +706,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (4/20) | 5.93 s
-[Task 1/25] Current/Best: 6.16/ 17.45 GFLOPS | Progress: (8/20) | 9.53 s
-[Task 1/25] Current/Best: 11.51/ 22.76 GFLOPS | Progress: (12/20) | 11.98 s
-[Task 1/25] Current/Best: 16.44/ 22.76 GFLOPS | Progress: (16/20) | 13.68 s
-[Task 1/25] Current/Best: 11.57/ 23.82 GFLOPS | Progress: (20/20) | 15.42 s Done.
+[Task 1/25] Current/Best: 17.57/ 17.57 GFLOPS | Progress: (4/20) | 6.30 s
+[Task 1/25] Current/Best: 6.16/ 17.57 GFLOPS | Progress: (8/20) | 9.32 s
+[Task 1/25] Current/Best: 11.53/ 22.69 GFLOPS | Progress: (12/20) | 11.74 s
+[Task 1/25] Current/Best: 16.54/ 22.87 GFLOPS | Progress: (16/20) | 13.42 s
+[Task 1/25] Current/Best: 11.60/ 23.86 GFLOPS | Progress: (20/20) | 15.15 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.08/ 12.90 GFLOPS | Progress: (4/20) | 3.88 s
-[Task 2/25] Current/Best: 14.26/ 18.00 GFLOPS | Progress: (8/20) | 5.18 s
-[Task 2/25] Current/Best: 21.28/ 21.28 GFLOPS | Progress: (12/20) | 6.51 s
-[Task 2/25] Current/Best: 12.23/ 21.28 GFLOPS | Progress: (16/20) | 7.76 s
-[Task 2/25] Current/Best: 19.39/ 21.28 GFLOPS | Progress: (20/20) | 9.40 s Done.
+[Task 2/25] Current/Best: 12.28/ 13.36 GFLOPS | Progress: (4/20) | 3.81 s
+[Task 2/25] Current/Best: 14.25/ 18.80 GFLOPS | Progress: (8/20) | 5.09 s
+[Task 2/25] Current/Best: 21.00/ 21.00 GFLOPS | Progress: (12/20) | 6.40 s
+[Task 2/25] Current/Best: 12.10/ 21.00 GFLOPS | Progress: (16/20) | 7.65 s
+[Task 2/25] Current/Best: 18.63/ 21.00 GFLOPS | Progress: (20/20) | 9.23 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.63/ 10.80 GFLOPS | Progress: (4/20) | 5.92 s
-[Task 3/25] Current/Best: 15.31/ 16.81 GFLOPS | Progress: (8/20) | 7.85 s
-[Task 3/25] Current/Best: 14.97/ 16.81 GFLOPS | Progress: (12/20) | 9.62 s
-[Task 3/25] Current/Best: 7.14/ 23.71 GFLOPS | Progress: (16/20) | 11.54 s
-[Task 3/25] Current/Best: 12.12/ 23.71 GFLOPS | Progress: (20/20) | 16.09 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.84 GFLOPS | Progress: (4/20) | 5.86 s
+[Task 3/25] Current/Best: 15.36/ 16.81 GFLOPS | Progress: (8/20) | 7.78 s
+[Task 3/25] Current/Best: 15.00/ 16.81 GFLOPS | Progress: (12/20) | 9.48 s
+[Task 3/25] Current/Best: 7.23/ 23.77 GFLOPS | Progress: (16/20) | 11.40 s
+[Task 3/25] Current/Best: 12.63/ 23.77 GFLOPS | Progress: (20/20) | 15.93 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.53/ 20.31 GFLOPS | Progress: (4/20) | 2.46 s
-[Task 4/25] Current/Best: 6.53/ 20.31 GFLOPS | Progress: (8/20) | 6.89 s
-[Task 4/25] Current/Best: 21.93/ 21.93 GFLOPS | Progress: (12/20) | 11.54 s
-[Task 4/25] Current/Best: 15.27/ 21.93 GFLOPS | Progress: (16/20) | 13.82 s
-[Task 4/25] Current/Best: 13.40/ 21.93 GFLOPS | Progress: (20/20) | 15.73 s Done.
+[Task 4/25] Current/Best: 9.40/ 18.03 GFLOPS | Progress: (4/20) | 2.41 s
+[Task 4/25] Current/Best: 6.83/ 18.03 GFLOPS | Progress: (8/20) | 6.79 s
+[Task 4/25] Current/Best: 22.13/ 22.13 GFLOPS | Progress: (12/20) | 11.30 s
+[Task 4/25] Current/Best: 16.54/ 22.13 GFLOPS | Progress: (16/20) | 13.55 s
+[Task 4/25] Current/Best: 13.34/ 22.13 GFLOPS | Progress: (20/20) | 15.53 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.59/ 10.15 GFLOPS | Progress: (4/20) | 2.66 s
-[Task 5/25] Current/Best: 11.52/ 12.42 GFLOPS | Progress: (8/20) | 4.75 s
-[Task 5/25] Current/Best: 11.04/ 18.01 GFLOPS | Progress: (12/20) | 7.74 s
-[Task 5/25] Current/Best: 11.91/ 22.53 GFLOPS | Progress: (16/20) | 9.16 s
-[Task 5/25] Current/Best: 12.07/ 22.53 GFLOPS | Progress: (20/20) | 11.05 s Done.
+[Task 5/25] Current/Best: 9.43/ 10.25 GFLOPS | Progress: (4/20) | 2.61 s
+[Task 5/25] Current/Best: 11.73/ 12.76 GFLOPS | Progress: (8/20) | 4.68 s
+[Task 5/25] Current/Best: 11.87/ 18.13 GFLOPS | Progress: (12/20) | 7.76 s
+[Task 5/25] Current/Best: 11.77/ 22.47 GFLOPS | Progress: (16/20) | 9.20 s
+[Task 5/25] Current/Best: 11.93/ 22.47 GFLOPS | Progress: (20/20) | 11.05 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.10/ 20.68 GFLOPS | Progress: (4/20) | 4.07 s
-[Task 6/25] Current/Best: 18.94/ 20.68 GFLOPS | Progress: (8/20) | 5.82 s
-[Task 6/25] Current/Best: 13.17/ 20.68 GFLOPS | Progress: (12/20) | 7.76 s
-[Task 6/25] Current/Best: 19.93/ 20.68 GFLOPS | Progress: (16/20) | 10.02 s
-[Task 6/25] Current/Best: 3.73/ 20.68 GFLOPS | Progress: (20/20) | 12.54 s Done.
+[Task 6/25] Current/Best: 12.16/ 20.71 GFLOPS | Progress: (4/20) | 3.96 s
+[Task 6/25] Current/Best: 19.01/ 20.71 GFLOPS | Progress: (8/20) | 5.72 s
+[Task 6/25] Current/Best: 13.36/ 20.71 GFLOPS | Progress: (12/20) | 7.64 s
+[Task 6/25] Current/Best: 19.99/ 20.71 GFLOPS | Progress: (16/20) | 9.89 s
+[Task 6/25] Current/Best: 3.72/ 20.71 GFLOPS | Progress: (20/20) | 12.40 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.11/ 12.89 GFLOPS | Progress: (4/20) | 3.71 s
-[Task 7/25] Current/Best: 20.19/ 20.90 GFLOPS | Progress: (8/20) | 5.25 s
-[Task 7/25] Current/Best: 15.89/ 20.90 GFLOPS | Progress: (12/20) | 7.17 s
-[Task 7/25] Current/Best: 12.24/ 20.90 GFLOPS | Progress: (16/20) | 9.24 s
-[Task 7/25] Current/Best: 6.40/ 21.69 GFLOPS | Progress: (20/20) | 11.72 s Done.
+[Task 7/25] Current/Best: 11.03/ 12.92 GFLOPS | Progress: (4/20) | 3.53 s
+[Task 7/25] Current/Best: 20.25/ 21.09 GFLOPS | Progress: (8/20) | 5.04 s
+[Task 7/25] Current/Best: 15.96/ 21.09 GFLOPS | Progress: (12/20) | 6.94 s
+[Task 7/25] Current/Best: 12.26/ 21.09 GFLOPS | Progress: (16/20) | 8.98 s
+[Task 7/25] Current/Best: 6.34/ 21.80 GFLOPS | Progress: (20/20) | 11.45 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.14/ 13.96 GFLOPS | Progress: (4/20) | 3.00 s
-[Task 8/25] Current/Best: 9.62/ 13.96 GFLOPS | Progress: (8/20) | 7.79 s
-[Task 8/25] Current/Best: 13.03/ 13.96 GFLOPS | Progress: (12/20) | 13.99 s
-[Task 8/25] Current/Best: 18.76/ 18.76 GFLOPS | Progress: (16/20) | 16.11 s
-[Task 8/25] Current/Best: 19.72/ 19.72 GFLOPS | Progress: (20/20) | 22.76 s Done.
+[Task 8/25] Current/Best: 9.43/ 14.05 GFLOPS | Progress: (4/20) | 2.93 s
+[Task 8/25] Current/Best: 9.17/ 14.05 GFLOPS | Progress: (8/20) | 7.80 s
+[Task 8/25] Current/Best: 12.61/ 14.05 GFLOPS | Progress: (12/20) | 13.93 s
+[Task 8/25] Current/Best: 18.72/ 18.72 GFLOPS | Progress: (16/20) | 16.02 s
+[Task 8/25] Current/Best: 19.55/ 19.55 GFLOPS | Progress: (20/20) | 22.59 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.28/ 14.95 GFLOPS | Progress: (4/20) | 12.03 s
-[Task 9/25] Current/Best: 23.28/ 23.28 GFLOPS | Progress: (8/20) | 13.85 s
-[Task 9/25] Current/Best: 8.24/ 23.28 GFLOPS | Progress: (12/20) | 16.25 s
-[Task 9/25] Current/Best: 17.86/ 23.28 GFLOPS | Progress: (16/20) | 18.96 s
-[Task 9/25] Current/Best: 9.19/ 23.28 GFLOPS | Progress: (20/20) | 26.84 s
+[Task 9/25] Current/Best: 14.31/ 15.40 GFLOPS | Progress: (4/20) | 11.95 s
+[Task 9/25] Current/Best: 23.47/ 23.47 GFLOPS | Progress: (8/20) | 13.75 s
+[Task 9/25] Current/Best: 8.25/ 23.47 GFLOPS | Progress: (12/20) | 16.10 s
+[Task 9/25] Current/Best: 17.70/ 23.47 GFLOPS | Progress: (16/20) | 18.75 s
+[Task 9/25] Current/Best: 9.22/ 23.47 GFLOPS | Progress: (20/20) | 26.38 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.42/ 18.42 GFLOPS | Progress: (4/20) | 2.62 s
-[Task 10/25] Current/Best: 15.50/ 18.42 GFLOPS | Progress: (8/20) | 4.25 s
-[Task 10/25] Current/Best: 12.35/ 19.25 GFLOPS | Progress: (12/20) | 5.79 s
-[Task 10/25] Current/Best: 19.14/ 20.39 GFLOPS | Progress: (16/20) | 6.91 s
-[Task 10/25] Current/Best: 8.83/ 20.39 GFLOPS | Progress: (20/20) | 8.47 s Done.
+[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.60 s
+[Task 10/25] Current/Best: 15.53/ 18.20 GFLOPS | Progress: (8/20) | 4.16 s
+[Task 10/25] Current/Best: 12.34/ 18.92 GFLOPS | Progress: (12/20) | 5.68 s
+[Task 10/25] Current/Best: 19.19/ 20.23 GFLOPS | Progress: (16/20) | 6.79 s
+[Task 10/25] Current/Best: 8.78/ 20.23 GFLOPS | Progress: (20/20) | 8.32 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.36/ 18.26 GFLOPS | Progress: (4/20) | 3.40 s
-[Task 11/25] Current/Best: 16.67/ 18.26 GFLOPS | Progress: (8/20) | 6.15 s
-[Task 11/25] Current/Best: 18.16/ 18.26 GFLOPS | Progress: (12/20) | 8.20 s
-[Task 11/25] Current/Best: 13.46/ 20.94 GFLOPS | Progress: (16/20) | 10.94 s
-[Task 11/25] Current/Best: 19.45/ 21.62 GFLOPS | Progress: (20/20) | 12.99 s Done.
+[Task 11/25] Current/Best: 12.30/ 18.27 GFLOPS | Progress: (4/20) | 3.32 s
+[Task 11/25] Current/Best: 15.86/ 18.27 GFLOPS | Progress: (8/20) | 6.06 s
+[Task 11/25] Current/Best: 17.91/ 18.27 GFLOPS | Progress: (12/20) | 8.13 s
+[Task 11/25] Current/Best: 13.58/ 20.95 GFLOPS | Progress: (16/20) | 10.84 s
+[Task 11/25] Current/Best: 19.45/ 21.61 GFLOPS | Progress: (20/20) | 12.88 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.76/ 18.20 GFLOPS | Progress: (4/20) | 5.43 s
-[Task 12/25] Current/Best: 5.21/ 18.20 GFLOPS | Progress: (8/20) | 9.14 s
-[Task 12/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (12/20) | 11.14 s
-[Task 12/25] Current/Best: 15.10/ 19.04 GFLOPS | Progress: (16/20) | 13.96 s
-[Task 12/25] Current/Best: 15.08/ 19.04 GFLOPS | Progress: (20/20) | 15.93 s Done.
+[Task 12/25] Current/Best: 7.84/ 17.87 GFLOPS | Progress: (4/20) | 5.35 s
+[Task 12/25] Current/Best: 5.23/ 17.87 GFLOPS | Progress: (8/20) | 9.01 s
+[Task 12/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (12/20) | 11.01 s
+[Task 12/25] Current/Best: 15.47/ 18.91 GFLOPS | Progress: (16/20) | 13.76 s
+[Task 12/25] Current/Best: 15.12/ 18.91 GFLOPS | Progress: (20/20) | 15.68 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.67/ 17.14 GFLOPS | Progress: (4/20) | 3.78 s
-[Task 13/25] Current/Best: 15.60/ 20.86 GFLOPS | Progress: (8/20) | 6.24 s
-[Task 13/25] Current/Best: 19.67/ 21.30 GFLOPS | Progress: (12/20) | 9.15 s
-[Task 13/25] Current/Best: 12.21/ 21.30 GFLOPS | Progress: (16/20) | 12.56 s
-[Task 13/25] Current/Best: 18.52/ 21.30 GFLOPS | Progress: (20/20) | 14.80 s Done.
+[Task 13/25] Current/Best: 8.87/ 17.29 GFLOPS | Progress: (4/20) | 3.64 s
+[Task 13/25] Current/Best: 14.89/ 21.03 GFLOPS | Progress: (8/20) | 6.07 s
+[Task 13/25] Current/Best: 19.72/ 21.36 GFLOPS | Progress: (12/20) | 9.01 s
+[Task 13/25] Current/Best: 12.29/ 21.36 GFLOPS | Progress: (16/20) | 12.40 s
+[Task 13/25] Current/Best: 18.69/ 21.36 GFLOPS | Progress: (20/20) | 14.65 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (4/20) | 3.38 s
-[Task 14/25] Current/Best: 6.08/ 13.64 GFLOPS | Progress: (8/20) | 5.56 s
-[Task 14/25] Current/Best: 20.05/ 20.05 GFLOPS | Progress: (12/20) | 8.12 s
-[Task 14/25] Current/Best: 17.32/ 20.05 GFLOPS | Progress: (16/20) | 9.81 s Done.
+[Task 14/25] Current/Best: 13.73/ 13.73 GFLOPS | Progress: (4/20) | 3.24 s
+[Task 14/25] Current/Best: 6.12/ 13.73 GFLOPS | Progress: (8/20) | 5.44 s
+[Task 14/25] Current/Best: 19.97/ 19.97 GFLOPS | Progress: (12/20) | 7.99 s
+[Task 14/25] Current/Best: 17.39/ 19.97 GFLOPS | Progress: (16/20) | 9.64 s Done.
-[Task 14/25] Current/Best: 17.02/ 20.05 GFLOPS | Progress: (20/20) | 11.61 s
+[Task 14/25] Current/Best: 17.28/ 19.97 GFLOPS | Progress: (20/20) | 11.39 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.19/ 17.62 GFLOPS | Progress: (4/20) | 2.82 s
-[Task 15/25] Current/Best: 14.32/ 17.97 GFLOPS | Progress: (8/20) | 4.12 s
-[Task 15/25] Current/Best: 10.35/ 22.31 GFLOPS | Progress: (12/20) | 6.23 s
-[Task 15/25] Current/Best: 20.23/ 22.31 GFLOPS | Progress: (16/20) | 9.22 s
-[Task 15/25] Current/Best: 9.66/ 22.31 GFLOPS | Progress: (20/20) | 10.20 s
+[Task 15/25] Current/Best: 16.17/ 17.66 GFLOPS | Progress: (4/20) | 2.74 s
+[Task 15/25] Current/Best: 14.51/ 17.99 GFLOPS | Progress: (8/20) | 4.08 s
+[Task 15/25] Current/Best: 10.37/ 22.35 GFLOPS | Progress: (12/20) | 6.14 s
+[Task 15/25] Current/Best: 20.35/ 22.35 GFLOPS | Progress: (16/20) | 9.08 s
+[Task 15/25] Current/Best: 9.69/ 22.35 GFLOPS | Progress: (20/20) | 10.05 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (4/20) | 3.03 s
-[Task 16/25] Current/Best: 3.04/ 20.46 GFLOPS | Progress: (8/20) | 4.68 s
-[Task 16/25] Current/Best: 18.78/ 20.46 GFLOPS | Progress: (12/20) | 5.91 s
-[Task 16/25] Current/Best: 17.59/ 20.46 GFLOPS | Progress: (16/20) | 7.26 s
-[Task 16/25] Current/Best: 10.04/ 21.80 GFLOPS | Progress: (20/20) | 9.34 s Done.
+[Task 16/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (4/20) | 2.94 s
+[Task 16/25] Current/Best: 3.00/ 20.26 GFLOPS | Progress: (8/20) | 4.56 s
+[Task 16/25] Current/Best: 18.76/ 20.26 GFLOPS | Progress: (12/20) | 5.79 s
+[Task 16/25] Current/Best: 17.42/ 20.26 GFLOPS | Progress: (16/20) | 7.12 s
+[Task 16/25] Current/Best: 10.01/ 21.93 GFLOPS | Progress: (20/20) | 9.14 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 14.06/ 18.31 GFLOPS | Progress: (4/20) | 4.79 s
-[Task 17/25] Current/Best: 14.43/ 23.17 GFLOPS | Progress: (8/20) | 7.69 s
-[Task 17/25] Current/Best: 17.93/ 23.17 GFLOPS | Progress: (12/20) | 9.75 s
-[Task 17/25] Current/Best: 16.38/ 23.17 GFLOPS | Progress: (16/20) | 11.91 s
-[Task 17/25] Current/Best: 10.02/ 23.17 GFLOPS | Progress: (20/20) | 14.06 s Done.
+[Task 17/25] Current/Best: 12.99/ 18.39 GFLOPS | Progress: (4/20) | 4.69 s
+[Task 17/25] Current/Best: 14.16/ 23.29 GFLOPS | Progress: (8/20) | 7.46 s
+[Task 17/25] Current/Best: 17.15/ 23.29 GFLOPS | Progress: (12/20) | 9.52 s
+[Task 17/25] Current/Best: 16.59/ 23.29 GFLOPS | Progress: (16/20) | 11.65 s
+[Task 17/25] Current/Best: 10.04/ 23.29 GFLOPS | Progress: (20/20) | 13.77 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.55/ 17.06 GFLOPS | Progress: (4/20) | 3.79 s
-[Task 18/25] Current/Best: 10.52/ 19.03 GFLOPS | Progress: (8/20) | 7.30 s
-[Task 18/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (12/20) | 9.27 s
-[Task 18/25] Current/Best: 10.02/ 19.04 GFLOPS | Progress: (16/20) | 12.90 s
-[Task 18/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (20/20) | 14.41 s Done.
+[Task 18/25] Current/Best: 11.33/ 17.96 GFLOPS | Progress: (4/20) | 3.68 s
+[Task 18/25] Current/Best: 10.61/ 17.96 GFLOPS | Progress: (8/20) | 7.11 s
+[Task 18/25] Current/Best: 19.26/ 19.26 GFLOPS | Progress: (12/20) | 9.03 s
+[Task 18/25] Current/Best: 10.04/ 19.26 GFLOPS | Progress: (16/20) | 12.59 s
+[Task 18/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (20/20) | 14.11 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 6.83/ 20.35 GFLOPS | Progress: (4/20) | 6.18 s
-[Task 19/25] Current/Best: 2.69/ 20.35 GFLOPS | Progress: (8/20) | 9.46 s
-[Task 19/25] Current/Best: 19.85/ 21.16 GFLOPS | Progress: (12/20) | 12.26 s
-[Task 19/25] Current/Best: 15.30/ 21.68 GFLOPS | Progress: (16/20) | 15.08 s
-[Task 19/25] Current/Best: 2.70/ 22.49 GFLOPS | Progress: (20/20) | 17.89 s Done.
+[Task 19/25] Current/Best: 7.16/ 20.27 GFLOPS | Progress: (4/20) | 6.00 s
+[Task 19/25] Current/Best: 2.69/ 20.27 GFLOPS | Progress: (8/20) | 9.28 s
+[Task 19/25] Current/Best: 18.71/ 21.69 GFLOPS | Progress: (12/20) | 12.11 s
+[Task 19/25] Current/Best: 14.08/ 21.69 GFLOPS | Progress: (16/20) | 15.00 s
+[Task 19/25] Current/Best: 2.70/ 23.34 GFLOPS | Progress: (20/20) | 17.89 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.51/ 15.08 GFLOPS | Progress: (4/20) | 3.39 s Done.
+[Task 20/25] Current/Best: 9.01/ 15.11 GFLOPS | Progress: (4/20) | 3.33 s Done.
Done.
-[Task 20/25] Current/Best: 10.49/ 15.08 GFLOPS | Progress: (8/20) | 6.85 s
-[Task 20/25] Current/Best: 2.32/ 15.08 GFLOPS | Progress: (12/20) | 10.80 s
-[Task 20/25] Current/Best: 12.44/ 15.08 GFLOPS | Progress: (16/20) | 14.37 s
-[Task 20/25] Current/Best: 13.14/ 21.89 GFLOPS | Progress: (20/20) | 16.48 s
+[Task 20/25] Current/Best: 9.65/ 15.11 GFLOPS | Progress: (8/20) | 6.67 s
+[Task 20/25] Current/Best: 2.27/ 15.33 GFLOPS | Progress: (12/20) | 10.60 s
+[Task 20/25] Current/Best: 12.26/ 15.33 GFLOPS | Progress: (16/20) | 14.33 s
+[Task 20/25] Current/Best: 12.49/ 22.26 GFLOPS | Progress: (20/20) | 16.40 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.38/ 17.66 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 21/25] Current/Best: 14.57/ 17.66 GFLOPS | Progress: (8/20) | 4.91 s
-[Task 21/25] Current/Best: 1.61/ 17.66 GFLOPS | Progress: (12/20) | 7.08 s
-[Task 21/25] Current/Best: 17.85/ 17.85 GFLOPS | Progress: (16/20) | 10.61 s
-[Task 21/25] Current/Best: 4.47/ 17.85 GFLOPS | Progress: (20/20) | 17.66 s
+[Task 21/25] Current/Best: 6.41/ 17.68 GFLOPS | Progress: (4/20) | 3.23 s
+[Task 21/25] Current/Best: 14.65/ 17.68 GFLOPS | Progress: (8/20) | 4.78 s
+[Task 21/25] Current/Best: 1.61/ 17.68 GFLOPS | Progress: (12/20) | 6.92 s
+[Task 21/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (16/20) | 10.36 s
+[Task 21/25] Current/Best: 4.48/ 18.04 GFLOPS | Progress: (20/20) | 17.42 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 17.11 GFLOPS | Progress: (4/20) | 2.75 s
-[Task 22/25] Current/Best: 8.81/ 21.92 GFLOPS | Progress: (8/20) | 4.74 s
-[Task 22/25] Current/Best: 19.95/ 21.92 GFLOPS | Progress: (12/20) | 7.05 s
-[Task 22/25] Current/Best: 15.24/ 21.92 GFLOPS | Progress: (16/20) | 9.11 s
-[Task 22/25] Current/Best: 14.26/ 21.92 GFLOPS | Progress: (20/20) | 10.79 s Done.
+[Task 22/25] Current/Best: 2.70/ 17.08 GFLOPS | Progress: (4/20) | 2.68 s
+[Task 22/25] Current/Best: 8.64/ 21.85 GFLOPS | Progress: (8/20) | 4.67 s
+[Task 22/25] Current/Best: 20.04/ 21.85 GFLOPS | Progress: (12/20) | 6.99 s
+[Task 22/25] Current/Best: 15.43/ 21.85 GFLOPS | Progress: (16/20) | 9.02 s
+[Task 22/25] Current/Best: 13.95/ 21.85 GFLOPS | Progress: (20/20) | 10.73 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.45/ 20.36 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 23/25] Current/Best: 15.53/ 20.36 GFLOPS | Progress: (8/20) | 6.67 s
-[Task 23/25] Current/Best: 20.86/ 21.42 GFLOPS | Progress: (12/20) | 8.51 s
-[Task 23/25] Current/Best: 6.37/ 21.42 GFLOPS | Progress: (16/20) | 15.67 s
-[Task 23/25] Current/Best: 7.63/ 21.42 GFLOPS | Progress: (20/20) | 19.92 s Done.
+[Task 23/25] Current/Best: 17.76/ 20.91 GFLOPS | Progress: (4/20) | 3.26 s
+[Task 23/25] Current/Best: 14.08/ 20.91 GFLOPS | Progress: (8/20) | 6.54 s
+[Task 23/25] Current/Best: 20.98/ 21.79 GFLOPS | Progress: (12/20) | 8.33 s
+[Task 23/25] Current/Best: 6.38/ 21.79 GFLOPS | Progress: (16/20) | 15.31 s
+[Task 23/25] Current/Best: 7.94/ 21.79 GFLOPS | Progress: (20/20) | 19.48 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.29/ 8.29 GFLOPS | Progress: (4/20) | 11.86 s
-[Task 24/25] Current/Best: 2.04/ 8.29 GFLOPS | Progress: (8/20) | 22.94 s
-[Task 24/25] Current/Best: 4.55/ 8.29 GFLOPS | Progress: (12/20) | 34.52 s Done.
+[Task 24/25] Current/Best: 8.23/ 8.23 GFLOPS | Progress: (4/20) | 11.81 s
+[Task 24/25] Current/Best: 2.15/ 8.23 GFLOPS | Progress: (8/20) | 22.87 s
+[Task 24/25] Current/Best: 4.07/ 8.23 GFLOPS | Progress: (12/20) | 34.42 s Done.
-[Task 24/25] Current/Best: 6.58/ 8.67 GFLOPS | Progress: (16/20) | 40.19 s
-[Task 24/25] Current/Best: 3.33/ 8.67 GFLOPS | Progress: (20/20) | 46.13 s Done.
+[Task 24/25] Current/Best: 6.03/ 8.58 GFLOPS | Progress: (16/20) | 39.69 s
+[Task 24/25] Current/Best: 3.42/ 8.81 GFLOPS | Progress: (20/20) | 45.70 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.86 GFLOPS | Progress: (4/20) | 11.65 s
-[Task 25/25] Current/Best: 5.67/ 7.71 GFLOPS | Progress: (8/20) | 22.99 s
-[Task 25/25] Current/Best: 5.86/ 7.71 GFLOPS | Progress: (12/20) | 34.46 s
-[Task 25/25] Current/Best: 5.72/ 8.46 GFLOPS | Progress: (16/20) | 36.21 s
-[Task 25/25] Current/Best: 2.81/ 8.67 GFLOPS | Progress: (20/20) | 46.90 s
+[Task 25/25] Current/Best: 1.55/ 2.74 GFLOPS | Progress: (4/20) | 11.60 s
+[Task 25/25] Current/Best: 6.06/ 8.55 GFLOPS | Progress: (8/20) | 22.84 s
+[Task 25/25] Current/Best: 6.07/ 8.55 GFLOPS | Progress: (12/20) | 34.25 s
+[Task 25/25] Current/Best: 5.90/ 8.68 GFLOPS | Progress: (16/20) | 35.97 s
+[Task 25/25] Current/Best: 2.87/ 8.92 GFLOPS | Progress: (20/20) | 46.69 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -943,8 +943,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621105
-class='n02123159 tiger cat' with probability=0.356377
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
+class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -981,8 +981,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 413.13507629001833, 'median': 413.24554720004016, 'std': 0.6239807331268357}
-unoptimized: {'mean': 498.8148181299857, 'median': 498.6909075999847, 'std': 0.5668175327660779}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 411.38670530000127, 'median': 411.50271740000335, 'std': 0.9684986889501206}
+unoptimized: {'mean': 490.990710279998, 'median': 490.65708260000065, 'std': 1.161852073224186}
</pre></div>
</div>
</div>
@@ -996,7 +996,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 23.303 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 11.264 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 7b6fc1b91..5fc4bc177 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.29e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.273e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index c28057168..14fa60e40 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x51974e0)), stage(b, placeholder(b, 0xde68f30)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[it [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xd32e000)), stage(b, placeholder(b, 0x207f2900)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</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 2c3aac373..08430be13 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:25.932</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:07.638</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,35 +336,35 @@
</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>10:23.303</p></td>
+<td><p>10:11.264</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>01:06.084</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
+<td><p>01:02.210</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.088</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
+<td><p>00:56.958</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:31.059</p></td>
+<td><p>00:30.278</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>00:23.989</p></td>
+<td><p>00:25.128</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.705</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.956</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.534</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.695</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>00:00.162</p></td>
+<td><p>00:00.141</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
@@ -372,7 +372,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.001</p></td>
+<td><p>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index d7313963f..cefba3ced 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -542,8 +542,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000006
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000009
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -668,10 +668,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.846030002838234e-06 1.0
- naive 5.8141e-06 0.7410244413922454
-parallel 6.0488000000000004e-06 0.7709376586390696
- vector 2.4599799999999998e-05 3.1353181151615823
+ numpy 9.040690001711482e-06 1.0
+ naive 6.5863e-06 0.7285174028479193
+parallel 5.9802e-06 0.6614760597772842
+ vector 2.4505399999999997e-05 2.7105674451132504
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -987,7 +987,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018652
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017712
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1030,7 +1030,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.340837
+none: 3.522438
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1097,7 +1097,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.306062
+blocking: 0.299239
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1158,7 +1158,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.343509
+vectorization: 0.338820
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1215,7 +1215,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.115733
+loop permutation: 0.113374
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1293,7 +1293,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.107636
+array packing: 0.108540
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1369,7 +1369,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.110511
+block caching: 0.110893
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1438,7 +1438,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.146145
+parallelization: 0.146482
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.3408365571000003 1.0
- blocking 0.3060615234 0.09161224087708003
- vectorization 0.34350862550000005 0.10282114064214543
-loop permutation 0.1157327619 0.034641850902296566
- array packing 0.10763585599999999 0.03221823461289973
- block caching 0.11051089239999998 0.03307880840957048
- parallelization 0.1461449957 0.043745030085177404
+ none 3.5224381027 1.0
+ blocking 0.2992390717 0.08495225834362538
+ vectorization 0.33881955480000003 0.09618893076936964
+loop permutation 0.1133744305 0.032186351383462736
+ array packing 0.1085400648 0.03081390265362008
+ block caching 0.110893463 0.03148201892177993
+ parallelization 0.1464820248 0.04158540775712124
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1538,7 +1538,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.088 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.210 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>