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 2022/08/17 23:44:20 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@c9a350c800809d9431c8b2b427e8f5af10a3ee89)
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 7199a1d28 deploying docs (apache/tvm@c9a350c800809d9431c8b2b427e8f5af10a3ee89)
7199a1d28 is described below
commit 7199a1d28b046375c170664d666062c1ae6cf9c0
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Aug 17 23:44:14 2022 +0000
deploying docs (apache/tvm@c9a350c800809d9431c8b2b427e8f5af10a3ee89)
---
docs/_sources/contribute/code_guide.rst.txt | 6 +-
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 590 +++++----------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 109 +++-
.../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 | 12 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 14 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 46 +-
docs/commit_hash | 2 +-
docs/contribute/code_guide.html | 6 +-
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 | 17 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 48 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 43 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 18 +-
.../tune_conv2d_layer_cuda.html | 590 +++++----------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 109 +++-
.../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 | 12 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 6 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 ++++-----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 28 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
123 files changed, 1254 insertions(+), 1804 deletions(-)
diff --git a/docs/_sources/contribute/code_guide.rst.txt b/docs/_sources/contribute/code_guide.rst.txt
index d404ba637..f60c6c829 100644
--- a/docs/_sources/contribute/code_guide.rst.txt
+++ b/docs/_sources/contribute/code_guide.rst.txt
@@ -148,12 +148,14 @@ server can go down or be slow), so try to avoid using the network at all during
this isn't a reasonable proposition (e.g. the docs tutorials which need to download models).
In these cases you can re-host files in S3 for fast access in CI. A committer can upload a file,
-specified by a name, hash, and path in S3, using the `workflow_dispatch` event on `the
+specified by a name, hash, and path in S3, using the ``workflow_dispatch`` event on `the
upload_ci_resource.yml GitHub Actions workflow
<https://github.com/apache/tvm/actions/workflows/upload_ci_resource.yml>`_. The sha256 must match
the file or it will not be uploaded. The upload path is user-defined so it can be any path (no
trailing or leading slashes allowed) but be careful not to collide with existing resources on
-accident.
+accident. Once uploaded you should send a PR to update the ``URL_MAP`` in
+`request_hook.py <https://github.com/apache/tvm/blob/main/tests/scripts/request_hook/request_hook.py>`_
+with the new URL.
Handle Integer Constant Expression
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 1a02fe230..2e5da57ac 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 6.100 seconds)
+ **Total running time of the script:** ( 1 minutes 4.889 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 c2643d9aa..c216f564f 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.zip00637364-3d26-453a-9826-34800b4484bb from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1bf5a0df-0d32-4f0b-a514-37dd0e126b40 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 ecd1c5c73..1960f8853 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, 55.3MB/s]
28%|##7 | 11.6M/41.5M [00:00<00:00, 34.8MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 27.7MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.0MB/s]
61%|######1 | 25.5M/41.5M [00:00<00:00, 29.2MB/s]
68%|######8 | 28.3M/41.5M [00:00<00:00, 28.1MB/s]
77%|#######7 | 32.1M/41.5M [00:01<00:00, 30.3MB/s]
85%|########4 | 35.1M/41.5M [00:01<00:00, 28.4MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 21.2MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 27.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 37.9MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 41.6MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 38.1MB/s]
63%|######2 | 26.0M/41.5M [00:00<00:00, 35.3MB/s]
77%|#######7 | 32.1M/41.5M [00:00<00:00, 42.5MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 18.9MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 27.1MB/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 4e2e5845c..3c4a82e50 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]
32%|###1 | 14.3M/44.7M [00:00<00:00, 150MB/s]
75%|#######4 | 33.3M/44.7M [00:00<00:00, 179MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 183MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
5%|5 | 2.29M/44.7M [00:00<00:01, 24.0MB/s]
12%|#1 | 5.30M/44.7M [00:00<00:01, 28.4MB/s]
35%|###5 | 15.8M/44.7M [00:00<00:00, 65.6MB/s]
62%|######1 | 27.5M/44.7M [00:00<00:00, 88.0MB/s]
88%|########7 | 39.2M/44.7M [00:00<00:00, 101MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 85.7MB/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 3a1a00ecf..39980b3bf 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.820 seconds)
+ **Total running time of the script:** ( 1 minutes 2.152 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index f672d123b..0bc8ab22c 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
=================
-**05:08.926** total execution time for **how_to_compile_models** files:
+**05:04.191** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:06.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:04.889 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.820 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.152 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.193 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.684 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.761 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.505 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.459 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.446 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.173 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:23.190 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.631 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.466 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.698 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.485 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.566 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.432 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.433 | 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 4bb2b0346..221f53a10 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)
- 16.1864 16.2044 16.3200 16.0568 0.0882
+ 15.8420 15.8727 16.1260 15.5095 0.2227
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 3ff4c0663..9a87b0e33 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 5.00M/170M [00:00<00:03, 52.4MB/s]
6%|5 | 10.0M/170M [00:00<00:03, 47.5MB/s]
9%|8 | 14.6M/170M [00:00<00:03, 47.0MB/s]
13%|#2 | 21.6M/170M [00:00<00:02, 56.6MB/s]
16%|#6 | 27.3M/170M [00:00<00:02, 57.2MB/s]
19%|#9 | 33.0M/170M [00:00<00:02, 58.0MB/s]
23%|##2 | 38.8M/170M [00:00<00:02, 58.7MB/s]
26%|##6 | 44.4M/170M [00:00<00:02, 53.2MB/s]
29%|##9 | 49.5M/170M [00:00<00:02, 50.1MB/s]
33%|###2 | 55.4M/170M [00:01<00:02, 53.4MB/s]
36%|###5 | 60.6M/170M [00:01<00:02, 49.5MB/s]
40%|###9 | 67.5M/170M [00:01<00:01, 55.6MB/s]
43%|####2 | 73.0M/170M [00:01<00:01, 54.7MB/s]
46%|####6 | 78.3M/170M [00:01<00:01, 54.7MB/s]
50%|####9 | 84.8M/170M [00:01<00:01, 58.6MB/s]
53%|#####3 | 90.5M/170M [00:01<00:01, 55.3MB/s]
56%|#####6 | 95.8M/170M [00:01<00:01, 52.9MB/
s]
60%|#####9 | 101M/170M [00:01<00:01, 53.9MB/s]
63%|######3 | 107M/170M [00:02<00:01, 56.1MB/s]
66%|######6 | 112M/170M [00:02<00:01, 47.8MB/s]
69%|######9 | 117M/170M [00:02<00:01, 47.9MB/s]
72%|#######1 | 122M/170M [00:02<00:01, 42.7MB/s]
74%|#######4 | 126M/170M [00:02<00:01, 41.0MB/s]
78%|#######7 | 132M/170M [00:02<00:00, 46.0MB/s]
81%|########1 | 138M/170M [00:02<00:00, 49.2MB/s]
84%|########3 | 143M/170M [00:02<00:00, 47.2MB/s]
87%|########6 | 147M/170M [00:03<00:00, 47.4MB/s]
90%|########9 | 153M/170M [00:03<00:00, 50.5MB/s]
94%|#########3| 159M/170M [00:03<00:00, 54.8MB/s]
97%|#########7| 165M/170M [00:03<00:00, 57.1MB/s]
100%|##########| 170M/170M [00:03<00:00, 52.0MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 5.09M/170M [00:00<00:03, 53.1MB/s]
10%|# | 17.6M/170M [00:00<00:01, 99.2MB/s]
18%|#7 | 30.1M/170M [00:00<00:01, 113MB/s]
25%|##5 | 42.5M/170M [00:00<00:01, 120MB/s]
32%|###2 | 55.0M/170M [00:00<00:00, 124MB/s]
40%|###9 | 67.1M/170M [00:00<00:00, 125MB/s]
47%|####6 | 79.1M/170M [00:00<00:00, 107MB/s]
54%|#####3 | 91.5M/170M [00:00<00:00, 113MB/s]
61%|######1 | 104M/170M [00:00<00:00, 118MB/s]
68%|######8 | 116M/170M [00:01<00:00, 121MB/s]
76%|#######5 | 129M/170M [00:01<00:00, 124MB/s]
83%|########2 | 141M/170M [00:01<00:00, 117MB/s]
89%|########9 | 152M/170M [00:01<00:00, 99.2MB/s]
97%|#########6| 164M/170M [00:01<00:00, 107MB/s]
100%|##########| 170M/170M [00:01<00:00, 112MB/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 3.485 seconds)
+ **Total running time of the script:** ( 2 minutes 57.299 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 5376ad771..388aa8f7f 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]
68%|######8 | 9.24M/13.6M [00:00<00:00, 96.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 113MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
35%|###5 | 4.77M/13.6M [00:00<00:00, 50.0MB/s]
89%|########8 | 12.0M/13.6M [00:00<00:00, 65.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 61.6MB/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)
- 90.4686 90.3536 93.4703 90.1925 0.3830
+ 90.3640 90.3067 91.7346 90.1768 0.2275
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.000 seconds)
+ **Total running time of the script:** ( 1 minutes 9.145 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 11c757752..afd6b1c2c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.7657 120.7669 123.5156 120.0525 0.4338
+ 119.5618 119.5291 122.5479 118.8665 0.4038
@@ -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 56.169 seconds)
+ **Total running time of the script:** ( 1 minutes 52.807 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 e821e7013..4e7e560cd 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 45.480 seconds)
+ **Total running time of the script:** ( 1 minutes 49.569 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 95bd31cdb..df445be85 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]
2%|1 | 2225/132723 [00:00<00:05, 22050.46KB/s]
4%|4 | 5813/132723 [00:00<00:04, 29847.11KB/s]
8%|8 | 10773/132723 [00:00<00:03, 38691.79KB/s]
13%|#3 | 17267/132723 [00:00<00:02, 48987.22KB/s]
18%|#8 | 24395/132723 [00:00<00:01, 56992.05KB/s]
24%|##3 | 31736/132723 [00:00<00:01, 62557.74KB/s]
29%|##9 | 38897/132723 [00:00<00:01, 65510.47KB/s]
35%|###4 | 46153/132723 [00:00<00:01, 67750.61KB/s]
40%|###9 | 52932/132723 [00:00<00:01, 57606.22KB/s]
45%|####5 | 60290/132723 [00:01<00:01, 61998.02KB/s]
51%|##### | 67518/132723 [00:01<00:01, 64896.39KB/s]
56%|#####6 | 74732/132723 [00:01<00:00, 66974.63KB/s]
62%|######1 | 81988/132723 [00:01<00:00, 68597.63KB/s]
67%|######7 | 89232/132723 [00:01<00:00, 69719.44KB/s]
73%|#######2 | 96543/132723 [00:01<00:00, 70717.84KB/s]
78%|#######8 |
104029/132723 [00:01<00:00, 71945.61KB/s]
84%|########3 | 111313/132723 [00:01<00:00, 72207.93KB/s]
89%|########9 | 118563/132723 [00:01<00:00, 57103.08KB/s]
95%|#########4| 125920/132723 [00:02<00:00, 61250.36KB/s]
100%|#########9| 132484/132723 [00:02<00:00, 28601.67KB/s]
100%|##########| 132723/132723 [00:02<00:00, 51028.58KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
2%|1 | 2449/132723 [00:00<00:05, 24487.75KB/s]
7%|6 | 8772/132723 [00:00<00:02, 47272.96KB/s]
10%|# | 13500/132723 [00:00<00:02, 45289.65KB/s]
14%|#4 | 18967/132723 [00:00<00:02, 48895.19KB/s]
20%|#9 | 26381/132723 [00:00<00:01, 57825.33KB/s]
25%|##5 | 33584/132723 [00:00<00:01, 62598.04KB/s]
31%|### | 40865/132723 [00:00<00:01, 65906.74KB/s]
36%|###6 | 48228/132723 [00:00<00:01, 68349.93KB/s]
42%|####1 | 55573/132723 [00:00<00:01, 69934.82KB/s]
47%|####7 | 62935/132723 [00:01<00:00, 71067.35KB/s]
53%|#####2 | 70326/132723 [00:01<00:00, 71934.75KB/s]
59%|#####8 | 77719/132723 [00:01<00:00, 72538.61KB/s]
64%|######4 | 85053/132723 [00:01<00:00, 72775.72KB/s]
70%|######9 | 92469/132723 [00:01<00:00, 73190.62KB/s]
75%|#######5 | 99867/132723 [00:01<00:00, 73426.88KB/s]
81%|######## |
107280/132723 [00:01<00:00, 73635.51KB/s]
86%|########6 | 114700/132723 [00:01<00:00, 73802.89KB/s]
92%|#########1| 122081/132723 [00:01<00:00, 73738.13KB/s]
98%|#########7| 129493/132723 [00:01<00:00, 73851.17KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67933.20KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 39.036 seconds)
+ **Total running time of the script:** ( 2 minutes 38.755 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 dc82999ba..718f54a43 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
=================
-**11:49.453** total execution time for **how_to_deploy_models** files:
+**11:42.456** 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``) | 03:03.485 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:57.299 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:39.036 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:38.755 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:56.169 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:52.807 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:45.480 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:49.569 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:09.145 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.446 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.283 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.641 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.567 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.189 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.026 | 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 f68639902..32ab9f04b 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.zip9f311937-81e4-4c8b-849a-0f708fe9d0fe from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip074202f6-18bf-4cda-8d4c-6a1f12011b63 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 10a57add7..c2dd64574 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:42.021** total execution time for **how_to_extend_tvm** files:
+**00:40.950** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.754 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.291 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.238 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.977 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.950 | 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 2de48dffd..018af849f 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: 6949us [6949us] (45.86%; 45.86%)
- FoldScaleAxis: 8202us [6us] (54.14%; 54.14%)
- FoldConstant: 8196us [1712us] (54.10%; 99.92%)
- InferType: 6484us [6484us] (42.80%; 79.12%)
+ InferType: 6779us [6779us] (46.18%; 46.18%)
+ FoldScaleAxis: 7900us [5us] (53.82%; 53.82%)
+ FoldConstant: 7895us [1675us] (53.78%; 99.93%)
+ InferType: 6220us [6220us] (42.37%; 78.78%)
@@ -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: 6484us [6484us] (44.32%; 44.32%)
- FoldScaleAxis: 8145us [5us] (55.68%; 55.68%)
- FoldConstant: 8140us [1720us] (55.64%; 99.94%)
- InferType: 6420us [6420us] (43.89%; 78.87%)
+ InferType: 6345us [6345us] (44.36%; 44.36%)
+ FoldScaleAxis: 7959us [4us] (55.64%; 55.64%)
+ FoldConstant: 7955us [1647us] (55.61%; 99.95%)
+ InferType: 6308us [6308us] (44.10%; 79.30%)
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 d3b4d03db..8e1f43670 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: 40.230610 ms
+ Convolution: 54.186297 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 cff9dc5ef..39d94b450 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: 7.084874 ms
+ conv2d with tensor core: 6.916246 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 f1657ab91..eb97e7cee 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: 0.019386
- Baseline: 3.389477
+ Numpy running time: 0.018752
+ Baseline: 3.545060
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.305083
+ Opt1: 0.302708
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.340637
+ Opt2: 0.329779
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116883
+ Opt3: 0.117075
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111949
+ Opt4: 0.111664
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111673
+ Opt5: 0.112647
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145606
+ Opt6: 0.145529
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 383c29e54..0acbb3f59 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
=================
-**00:34.582** total execution time for **how_to_optimize_operators** files:
+**00:34.799** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.382 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.615 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.217 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.198 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.984 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.986 | 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 96fa9560a..9ad7749b0 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
=================
-**06:10.051** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:23.310** 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``) | 03:22.661 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:25.189 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.797 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:47.363 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:47.024 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.596 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.482 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.991 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.915 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.827 | 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 816965b8c..94651f4b1 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,268 +240,72 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- 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
- conv2d_nchw_1[14] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[3] = 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[15] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- let cse_var_1: int32 = (rc.outer.outer*1568)
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [1]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [108]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_1: int32 = (rc.outer.outer*36)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 343), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 19), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 441), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 539), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 70), 81)) && (floormod((threadIdx.x_1 + 70), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 637), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 38), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 38), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 735)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 735), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 833), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 40), 81)) && (floormod((threadIdx.x_1 + 40), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 931), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 40), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 57), 81)) && (floormod((threadIdx.x_1 + 57), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1029), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 57), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else((((threadIdx.x_1 < 47) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @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_1 + (floordiv((threadIdx.x_1 + 1127), 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_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1225), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @tir.if_then_else((((threadIdx.x_1 < 45) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1323), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 3)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1372), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 44), 81)) && (floormod((threadIdx.x_1 + 44), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1421), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 44), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1470), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 61), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1519), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 61), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else((((threadIdx.x_1 < 43) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 78), 81)) && (floormod((threadIdx.x_1 + 78), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1617), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 78), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 46), 81)) && (floormod((threadIdx.x_1 + 46), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1666), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 46), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1715), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 14), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 7), 9)) && (floormod((threadIdx.x_1 + 63), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1764), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 7), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @tir.if_then_else((((threadIdx.x_1 < 41) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1813), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1862), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 48), 81)) && (floormod((threadIdx.x_1 + 48), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1911), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2009)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 65), 81)) && (floormod((threadIdx.x_1 + 65), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2009), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 33), 81)) && (floormod((threadIdx.x_1 + 33), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2058), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 33), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2107)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 1), 81)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2107), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 50), 81)) && (floormod((threadIdx.x_1 + 50), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2156), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 50), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2205)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2205), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2254), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2303)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 35), 81)) && (floormod((threadIdx.x_1 + 35), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2303), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 35), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2401)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 52), 81)) && (floormod((threadIdx.x_1 + 52), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2401), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 52), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2450), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2499)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 69), 81)) && (floormod((threadIdx.x_1 + 69), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2499), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 69), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2548), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod(th [...]
}
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 4) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24))] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + (threadIdx.x_2*8)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + ( [...]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 1)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + (threadIdx.x_2*8)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 2)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + (threadIdx.x_2*8)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 4)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 5)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 7)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 8)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 10)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 11)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 13)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 14)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 16)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 17)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 19)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 20)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 22)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 23)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 2)]
- }
- }
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ry.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 8) {
- let cse_var_9: int32 = (ff.outer.inner + 8)
- let cse_var_8: int32 = (ff.outer.inner + 6)
- let cse_var_7: int32 = (ff.outer.inner + 4)
- let cse_var_6: int32 = (ff.outer.inner + 2)
- let cse_var_5: int32 = (ff.outer.inner + 14)
- let cse_var_4: int32 = (ff.outer.inner + 12)
- let cse_var_3: int32 = (ff.outer.inner + 10)
- let cse_var_2: int32 = ((((ff.outer.inner*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3))
- {
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_2]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 576)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1152)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1728)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 2304)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 2880)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 3456)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 4032)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 577)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1153)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1729)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 2305)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 2881)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 3457)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 4033)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 578)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1154)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1730)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2306)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2882)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 3458)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 4034)]))
- }
- }
- }
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
}
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 30)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 31)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 32)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 33)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 34)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 57)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 58)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 59)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 60)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 61)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 62)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 35)]))
}
}
- for (i1.inner: int32, 0, 2) {
- compute[(((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*16) + i1.inner)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*16) + i1.inner) + 2)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*16) + i1.inner) + 4)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 294)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*16) + i1.inner) + 6)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 392)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*16) + i1.inner) + 8)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 490)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*16) + i1.inner) + 10)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 588)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*16) + i1.inner) + 12)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 686)] = max((conv2d_nchw_1[(i1.inner + 14)] + bias[(((blockIdx.x*16) + i1.inner) + 14)]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
@@ -555,7 +359,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.388 ms
+ Execution time of this operator: 0.406 ms
@@ -604,35 +408,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_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=8)
+ 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=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=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)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=8)
+ compute_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=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_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)
@@ -650,14 +454,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+ 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=49)
+ 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", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -677,201 +481,63 @@ 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__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[16];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[4608];
+ 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[1];
+ __shared__ float pad_temp_shared[108];
+ __shared__ float kernel_shared[1152];
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[14] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 441)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 637)] = (((((9 <= ((((int)threadIdx.x) + 70) % 81)) && (((((int)threadIdx.x) + 70) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 637) / 81) * 49)) + ((((((int)threadIdx.x) + 70) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 735)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 735) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 833)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 833) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((9 <= ((((int)threadIdx.x) + 40) % 81)) && (((((int)threadIdx.x) + 40) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 931) / 81) * 49)) + ((((((int)threadIdx.x) + 40) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 81) * 49)) + (((((int)threadIdx.x) + 8) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((9 <= ((((int)threadIdx.x) + 57) % 81)) && (((((int)threadIdx.x) + 57) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1029) / 81) * 49)) + ((((((int)threadIdx.x) + 57) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + (((((int)threadIdx.x) + 25) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1127) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1225) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((((int)threadIdx.x) < 45) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1323) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 13)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((9 <= ((((int)threadIdx.x) + 44) % 81)) && (((((int)threadIdx.x) + 44) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1421) / 81) * 49)) + ((((((int)threadIdx.x) + 44) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1519) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((((int)threadIdx.x) < 43) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + (((((int)threadIdx.x) + 29) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((9 <= ((((int)threadIdx.x) + 78) % 81)) && (((((int)threadIdx.x) + 78) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1617) / 81) * 49)) + ((((((int)threadIdx.x) + 78) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((9 <= ((((int)threadIdx.x) + 46) % 81)) && (((((int)threadIdx.x) + 46) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 81) * 49)) + ((((((int)threadIdx.x) + 46) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1715)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1715) / 81) * 49)) + (((((int)threadIdx.x) + 14) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) / 9) + 7) % 9)) && (((((int)threadIdx.x) + 63) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1764) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 7) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1813)] = ((((((int)threadIdx.x) < 41) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1813) / 81) * 49)) + (((((int)threadIdx.x) + 31) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1911) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + (((((int)threadIdx.x) + 16) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((9 <= ((((int)threadIdx.x) + 65) % 81)) && (((((int)threadIdx.x) + 65) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2009) / 81) * 49)) + ((((((int)threadIdx.x) + 65) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((9 <= ((((int)threadIdx.x) + 33) % 81)) && (((((int)threadIdx.x) + 33) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2058) / 81) * 49)) + ((((((int)threadIdx.x) + 33) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2107)] = ((((8 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2107) / 81) * 49)) + (((((int)threadIdx.x) + 1) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((9 <= ((((int)threadIdx.x) + 50) % 81)) && (((((int)threadIdx.x) + 50) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2156) / 81) * 49)) + ((((((int)threadIdx.x) + 50) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2205)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2205) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2254) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((9 <= ((((int)threadIdx.x) + 35) % 81)) && (((((int)threadIdx.x) + 35) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2303) / 81) * 49)) + ((((((int)threadIdx.x) + 35) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((6 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((((9 <= ((((int)threadIdx.x) + 52) % 81)) && (((((int)threadIdx.x) + 52) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2401) / 81) * 49)) + ((((((int)threadIdx.x) + 52) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2450) / 81) * 49)) + (((((int)threadIdx.x) + 20) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((9 <= ((((int)threadIdx.x) + 69) % 81)) && (((((int)threadIdx.x) + 69) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2499) / 81) * 49)) + ((((((int)threadIdx.x) + 69) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 44) {
- pad_temp_shared[(((int)threadIdx.x) + 2548)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2548) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 108) {
+ pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
}
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 4; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24))] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) * 8)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) * 8)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) * 8)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 4)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3 [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 5)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3 [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 7)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3 [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 8)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3 [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 10)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 11)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 13)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 14)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 16)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 17)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 19)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 20)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 22)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * [...]
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 23)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * [...]
- }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 576)]));
- conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1152)]));
- conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1728)]));
- conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2304)]));
- conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2880)]));
- conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 3456)]));
- conv2d_nchw[(ff_outer_inner + 14)] = (conv2d_nchw[(ff_outer_inner + 14)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 4032)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 577)]));
- conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1153)]));
- conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1729)]));
- conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2305)]));
- conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2881)]));
- conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 3457)]));
- conv2d_nchw[(ff_outer_inner + 14)] = (conv2d_nchw[(ff_outer_inner + 14)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 4033)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 578)]));
- conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1154)]));
- conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1730)]));
- conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2306)]));
- conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2882)]));
- conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 3458)]));
- conv2d_nchw[(ff_outer_inner + 14)] = (conv2d_nchw[(ff_outer_inner + 14)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 4034)]));
- }
- }
- }
- }
- }
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 2)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 4)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 294)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 6)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 8)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 490)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 10)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 12)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 686)] = max((conv2d_nchw[(i1_inner + 14)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 14)]), 0.000000e+00f);
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 30)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 31)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 32)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 33)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 34)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 57)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 58)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 59)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 60)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 61)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 62)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
}
+ compute[((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
@@ -932,7 +598,7 @@ 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 22.661 seconds)
+ **Total running time of the script:** ( 3 minutes 25.189 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 8f897d45b..58c9209e5 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)
- 9.7872 9.7959 9.8087 9.7568 0.0221
+ 9.8802 9.8940 9.8976 9.8490 0.0221
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 957161a66..eda3b6d74 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)
- 763.5554 761.6409 768.1319 760.8934 3.2504
+ 755.1005 753.8131 758.6839 752.8044 2.5671
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.419 seconds)
+ **Total running time of the script:** ( 1 minutes 22.797 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 642080075..4b9f0b128 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
@@ -397,30 +397,103 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 1024) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ 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, 2) {
- for (i.inner.init: int32, 0, 2) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [64], [])[(((i.outer.inner*32) + (i.inner.init*16)) + j.init)] = 0f32
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = ((i.outer.inner*1024) + (i.inner.init*16))
+ {
+ 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
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 2) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*32) + (i.inner*16)) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*1024) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 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, 64) {
+ 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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 4) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_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))
}
}
}
@@ -476,7 +549,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.900 ms
+ Execution time of this operator: 1.830 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 3e0ea00a4..472b20f50 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
=================
-**00:46.124** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.490** 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``) | 00:46.089 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.454 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_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 980829ef4..dc3ecd073 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: 175.34/175.34 result: MeasureResult(costs=(0.0013202865777777778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0665640830993652, timestamp=1660767589.506768) [('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: 0.00/175.34 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 174.79/174.79 result: MeasureResult(costs=(0.0013244358000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0026540756225586, timestamp=1660774528.6020384) [('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: 0.00/174.79 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.22/260.22 result: MeasureResult(costs=(0.000889643049723757,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7950384616851807, timestamp=1660767590.4355657) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.55/260.55 result: MeasureResult(costs=(0.0008885241325966852,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6772856712341309, timestamp=1660774529.5255716) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 5.45/260.22 result: MeasureResult(costs=(0.04244121325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8485305309295654, timestamp=1660767595.006558) [('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: 3.34/260.22 result: MeasureResult(costs=(0.069398374,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.563762187957764, timestamp=1660767596.242726) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.46/260.55 result: MeasureResult(costs=(0.04240317875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.854973316192627, timestamp=1660774534.1012974) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.35/260.55 result: MeasureResult(costs=(0.06914184450000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.570073127746582, timestamp=1660774535.3415718) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/260.55 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: 26.13/260.22 result: MeasureResult(costs=(0.008860859416666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1633820533752441, timestamp=1660767607.1559665) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 26.02/260.55 result: MeasureResult(costs=(0.008896619916666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1460175514221191, timestamp=1660774546.2641227) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 0.001276
+ Time cost of this operator: 0.001251
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 b45b59064..be2238c27 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 311.8 98.736 (1, 2, 10, 10, 3) 2 1 [311.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.019 0.956 (1, 6, 10, 10) 1 1 [3.019]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.308 (1, 1, 10, 10, 3) 1 1 [0.973]
- Total_time - 315.793 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.9 98.718 (1, 2, 10, 10, 3) 2 1 [311.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.089 0.978 (1, 6, 10, 10) 1 1 [3.089]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.305 (1, 1, 10, 10, 3) 1 1 [0.962]
+ Total_time - 315.951 - - - - -
@@ -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 79.312 96.686 (1, 6, 10, 10, 1) 2 1 [79.312]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.747 2.13 (1, 6, 10, 10) 1 1 [1.747]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 1.185 (1, 1, 10, 10, 3) 1 1 [0.972]
- Total_time - 82.031 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 89.75 97.007 (1, 6, 10, 10, 1) 2 1 [89.75]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.808 1.954 (1, 6, 10, 10) 1 1 [1.808]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 1.039 (1, 1, 10, 10, 3) 1 1 [0.961]
+ Total_time - 92.519 - - - - -
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 1cf27ea70..8bfd4fa34 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/tmp066vjjuv/images/random'
+ '/tmp/tmpwd3j6wag/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp066vjjuv/images/target contains 8144 images
- /tmp/tmp066vjjuv/images/random contains 5000 images
+ /tmp/tmpwd3j6wag/images/target contains 8144 images
+ /tmp/tmpwd3j6wag/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 56s - loss: 0.2254 - accuracy: 0.9272 - val_loss: 0.1711 - val_accuracy: 0.9551
+ 328/328 - 55s - loss: 0.2443 - accuracy: 0.9176 - val_loss: 0.1523 - val_accuracy: 0.9547
Epoch 2/3
- 328/328 - 53s - loss: 0.0985 - accuracy: 0.9619 - val_loss: 0.1269 - val_accuracy: 0.9611
+ 328/328 - 53s - loss: 0.0981 - accuracy: 0.9633 - val_loss: 0.1087 - val_accuracy: 0.9611
Epoch 3/3
- 328/328 - 52s - loss: 0.0680 - accuracy: 0.9748 - val_loss: 0.1298 - val_accuracy: 0.9577
+ 328/328 - 52s - loss: 0.0716 - accuracy: 0.9723 - val_loss: 0.1413 - val_accuracy: 0.9490
- <keras.callbacks.History object at 0x7fb5f980e390>
+ <keras.callbacks.History object at 0x7f193a00d590>
@@ -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:** ( 6 minutes 19.134 seconds)
+ **Total running time of the script:** ( 5 minutes 50.413 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 5518749e8..47c2c99ea 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
=================
-**07:13.180** total execution time for **how_to_work_with_microtvm** files:
+**06:43.812** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 06:19.134 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:50.413 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.664 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.370 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.018 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.737 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.363 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.290 | 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 cf64f3f15..c0b269e74 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.378** total execution time for **how_to_work_with_relay** files:
+**00:42.698** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.738 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.274 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.850 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.628 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.567 | 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 caeb8e134..6b22a08c8 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 0x7fb600c7a710>
+ <function my_cuda_math_rule at 0x7f189e876c20>
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 185c48c9d..5c80da62f 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**00:04.140** total execution time for **how_to_work_with_schedules** files:
+**00:04.075** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.905 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.874 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.989 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.973 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.537 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.529 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.522 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.513 | 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``) | 00:00.101 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.042 | 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 67d5966e8..c83bbd338 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/tmpxlv58kt1/input0.cc'\nsource_filename = \"/tmp/tmpxlv58kt1/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/tmpjx4rp4ok/input0.cc'\nsource_filename = \"/tmp/tmpjx4rp4ok/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 3aad57169..96a98b2e8 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:22.269** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.389** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.262 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.383 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index a58ab44b9..52cb15ea4 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 24.04s!
+ resnet18_v1 inference graph built in 23.25s!
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 ecd47c09d..3d360c88d 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.54s!
+ yolov3-tiny inference graph built in 16.11s!
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 6e62b0743..764b302e9 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
=================
-**01:34.785** total execution time for **topic_vta_tutorials_frontend** files:
+**01:32.813** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.432 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.248 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.353 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.565 | 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 55f8cb195..210738997 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
=================
-**00:03.293** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.243** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.887 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.846 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.406 | 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 92d0a5c4b..4ace5a5d1 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
=================
-**00:00.750** total execution time for **topic_vta_tutorials** files:
+**00:00.733** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.410 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.401 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.339 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.333 | 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 f55a13fed..6957cf3e7 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -205,13 +205,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E*E
-
-
@@ -335,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.436 ms
+ Execution time of this operator: 93.646 ms
@@ -451,11 +444,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 14.897 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 fd6c53fcf..057eebac3 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: 9.29/9.29 result: MeasureResult(costs=(0.0288849552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.600048303604126, timestamp=1660766322.7015827) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.52/9.29 result: MeasureResult(costs=(0.10672176559999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8620357513427734, timestamp=1660766325.1146002) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.80/11.80 result: MeasureResult(costs=(0.0227568016,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5922126770019531, timestamp=1660766325.6832175) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.64/11.80 result: MeasureResult(costs=(0.163207984,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.725649833679199, timestamp=1660766328.998544) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.64/11.80 result: MeasureResult(costs=(0.07382258359999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3251597881317139, timestamp=1660766330.454356) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.69/11.80 result: MeasureResult(costs=(0.159098199,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6759066581726074, timestamp=1660766333.7150173) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.80 result: MeasureResult(costs=(0.30979541599999993,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.079302549362183, timestamp=1660766338.8374858) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 9.92/11.80 result: MeasureResult(costs=(0.027051918,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5881311893463135, timestamp=1660766339.4348228) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.71/11.80 result: MeasureResult(costs=(0.1566016678,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6089847087860107, timestamp=1660766342.163791) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.68/11.80 result: MeasureResult(costs=(0.10009217740000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7074134349822998, timestamp=1660766343.9287486) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.37/9.37 result: MeasureResult(costs=(0.0286575798,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5934884548187256, timestamp=1660773303.7610288) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.23/9.37 result: MeasureResult(costs=(0.1204693158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.078216075897217, timestamp=1660773305.8544705) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.76/11.76 result: MeasureResult(costs=(0.0228277336,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5667085647583008, timestamp=1660773306.9233484) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.84/11.76 result: MeasureResult(costs=(0.1461202098,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.460383653640747, timestamp=1660773309.9600503) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.67/11.76 result: MeasureResult(costs=(0.0732128722,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3065061569213867, timestamp=1660773311.3973153) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.73/11.76 result: MeasureResult(costs=(0.1549511274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.598661422729492, timestamp=1660773314.567383) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.76 result: MeasureResult(costs=(0.3087661896,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.060447692871094, timestamp=1660773319.6701758) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.48/11.76 result: MeasureResult(costs=(0.0256123034,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5521392822265625, timestamp=1660773320.244423) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.89/11.76 result: MeasureResult(costs=(0.1417037224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3667666912078857, timestamp=1660773322.73113) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.77/11.76 result: MeasureResult(costs=(0.0970126398,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6593945026397705, timestamp=1660773324.4480147) [('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 70d2e3410..e986a816d 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 496.84622677000107, 'median': 496.8420989500032, 'std': 1.0463698614272814}
+ {'mean': 497.57861620000085, 'median': 497.59652024999923, 'std': 0.3718688564612551}
@@ -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: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 6.48 s
[Task 1/25] Current/Best: 6.16/ 17.41 GFLOPS | Progress: (8/20) | 9.44 s
[Task 1/25] Current/Best: 11.51/ 22.67 GFLOPS | Progress: (12/20) | 11.87 s
[Task 1/25] Current/Best: 16.73/ 22.67 GFLOPS | Progress: (16/20) | 13.57 s
[Task 1/25] Current/Best: 11.52/ 23.89 GFLOPS | Progress: (20/20) | 15.34 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.21/ 12.91 GFLOPS | Progress: (4/20) | 3.72 s
[Task 2/25] Current/Best: 14.18/ 18.82 GFLOPS | Progress: (8/20) | 5.03 s
[Task 2/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 6.36 s
[Task 2/25] Current/Best: 12.95/ 19.28 GFLOPS | Progress: (16/20) | 7.63 s
[Task 2/25] Current/Best: 19.52/ 19.52 GFLOPS | Progress: (20/20) | 9.26 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/ 10.57 GFLOPS | Progress: (4/20) | 5.91 s
[Task 3/25] Current/Best: 15.51/ 16.83 GFLOPS | Progress: (8/20) | 7.84 s
[Task 3/25] Current/Best: 14.80/ 16.83 GFLOPS | Progress: (12/20) | 9.60 s
[Task 3/25] Current/Best: 7.19/ 23.74 GFLOPS | Progress: (16/20) | 11.53 s
[Task 3/25] Current/Best: 12.61/ 23.74 GFLOPS | Progress: (20/20) | 16.06 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.57/ 20.44 GFLOPS | Progress: (4/20) | 2.46 s
[Task 4/25] Current/Best: 6.32/ 20.44 GFLOPS | Progress: (8/20) | 6.82 s
[Task 4/25] Current/Best: 21.91/ 21.91 GFLOPS | Progress: (12/20) | 11.31 s
[Task 4/25] Current/Best: 15.83/ 21.91 GFLOPS | Progress: (16/20) | 13.59 s
[Task 4/25] Current/Best: 13.09/ 21.91 GFLOPS | Progress: (20/20) | 15.60 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.66/ 10.23 GFLOPS | Progress: (4/20) | 2.65 s
[Task 5/25] Current/Best: 11.68/ 12.97 GFLOPS | Progress: (8/20) | 4.71 s
[Task 5/25] Current/Best: 10.64/ 17.93 GFLOPS | Progress: (12/20) | 7.85 s
[Task 5/25] Current/Best: 11.71/ 22.62 GFLOPS | Progress: (16/20) | 9.29 s
[Task 5/25] Current/Best: 11.90/ 22.62 GFLOPS | Progress: (20/20) | 11.17 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.18/ 20.76 GFLOPS | Progress: (4/20) | 4.06 s
[Task 6/25] Current/Best: 18.85/ 20.76 GFLOPS | Progress: (8/20) | 5.83 s
[Task 6/25] Current/Best: 13.29/ 20.76 GFLOPS | Progress: (12/20) | 7.76 s
[Task 6/25] Current/Best: 19.82/ 20.76 GFLOPS | Progress: (16/20) | 10.06 s
[Task 6/25] Current/Best: 3.75/ 20.76 GFLOPS | Progress: (20/20) | 12.57 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.09/ 12.85 GFLOPS | Progress: (4/20) | 3.68 s
[Task 7/25] Current/Best: 20.18/ 21.13 GFLOPS | Progress: (8/20) | 5.21 s
[Task 7/25] Current/Best: 15.91/ 21.13 GFLOPS | Progress: (12/20) | 7.17 s
[Task 7/25] Current/Best: 12.23/ 21.13 GFLOPS | Progress: (16/20) | 9.22 s
[Task 7/25] Current/Best: 6.38/ 21.72 GFLOPS | Progress: (20/20) | 11.69 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.89/ 14.40 GFLOPS | Progress: (4/20) | 3.03 s
[Task 8/25] Current/Best: 9.53/ 14.40 GFLOPS | Progress: (8/20) | 7.80 s
[Task 8/25] Current/Best: 12.85/ 14.40 GFLOPS | Progress: (12/20) | 13.99 s
[Task 8/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (16/20) | 16.11 s
[Task 8/25] Current/Best: 20.00/ 20.00 GFLOPS | Progress: (20/20) | 22.70 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.26/ 15.80 GFLOPS | Progress: (4/20) | 11.98 s
[Task 9/25] Current/Best: 23.45/ 23.45 GFLOPS | Progress: (8/20) | 13.77 s
[Task 9/25] Current/Best: 8.20/ 23.45 GFLOPS | Progress: (12/20) | 16.14 s
[Task 9/25] Current/Best: 17.79/ 23.45 GFLOPS | Progress: (16/20) | 18.84 s
[Task 9/25] Current/Best: 9.12/ 23.45 GFLOPS | Progress: (20/20) | 26.50 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/20) | 2.59 s
[Task 10/25] Current/Best: 15.56/ 18.31 GFLOPS | Progress: (8/20) | 4.18 s
[Task 10/25] Current/Best: 12.58/ 19.00 GFLOPS | Progress: (12/20) | 5.72 s
[Task 10/25] Current/Best: 18.60/ 20.21 GFLOPS | Progress: (16/20) | 6.84 s
[Task 10/25] Current/Best: 9.06/ 20.21 GFLOPS | Progress: (20/20
) | 8.38 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.62/ 18.10 GFLOPS | Progress: (4/20) | 3.42 s
[Task 11/25] Current/Best: 16.86/ 18.10 GFLOPS | Progress: (8/20) | 6.16 s
[Task 11/25] Current/Best: 18.10/ 18.10 GFLOPS | Progress: (12/20) | 8.25 s
[Task 11/25] Current/Best: 13.50/ 21.09 GFLOPS | Progress: (16/20) | 11.06 s
[Task 11/25] Current/Best: 19.40/ 21.53 GFLOPS | Progress: (20/20) | 13.09 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.78/ 18.14 GFLOPS | Progress: (4/20) | 5.45 s
[Task 12/25] Current/Best: 5.19/ 18.14 GFLOPS | Progress: (8/20) | 9.15 s
[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (12/20) | 11.17 s
[Task 12/25] Current/Best: 15.26/ 18.95 GFLOPS | Progress: (16/20) | 13.98 s
[Task 12/25] Current/Best: 15.07/ 18.95 GFLOPS | Progress: (20/20) | 15.90 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.88/ 17.19 GFLOPS | Progress: (4/20) | 3.69 s
[Task 13/25] Current/Best: 16.01/ 20.79 GFLOPS | Progress: (8/20) | 6.15 s
[Task 13/25] Current/Best: 19.11/ 21.70 GFLOPS | Progress: (12/20) | 9.10 s
[Task 13/25] Current/Best: 12.22/ 21.70 GFLOPS | Progress: (16/20) | 12.54 s
[Task 13/25] Current/Best: 18.50/ 21.70 GFLOPS | Progress: (20/20) | 14.79 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.61/ 13.61 GFLOPS | Progress: (4/20) | 3.30 s
[Task 14/25] Current/Best: 6.11/ 13.61 GFLOPS | Progress: (8/20) | 5.48 s
[Task 14/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (12/20) | 8.06 s
[Task 14/25] Current/Best: 15.55/ 20.81 GFLOPS | Progress: (16/20) | 9.72 s Done.
-
[Task 14/25] Current/Best: 17.24/ 20.81 GFLOPS | Progress: (20/20) | 11.47 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.05/ 17.64 GFLOPS | Progress: (4/20) | 2.78 s
[Task 15/25] Current/Best: 14.19/ 17.97 GFLOPS | Progress: (8/20) | 4.09 s
[Task 15/25] Current/Best: 10.37/ 22.19 GFLOPS | Progress: (12/20) | 6.27 s
[Task 15/25] Current/Best: 20.21/ 22.19 GFLOPS | Progress: (16/20) | 9.16 s
[Task 15/25] Current/Best: 9.69/ 22.19 GFLOPS | Progress: (20/20) | 10.14 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (4/20) | 3.04 s
[Task 16/25] Current/Best: 3.04/ 19.90 GFLOPS | Progress: (8/20) | 4.66 s
[Task 16/25] Current/Best: 19.27/ 19.90 GFLOPS | Progress: (12/20) | 5.89 s
[Task 16/25] Current/Best: 17.85/ 19.90 GFLOPS | Progress: (16/20) |
7.23 s
[Task 16/25] Current/Best: 9.96/ 22.49 GFLOPS | Progress: (20/20) | 9.28 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.98/ 18.82 GFLOPS | Progress: (4/20) | 4.77 s
[Task 17/25] Current/Best: 14.48/ 22.95 GFLOPS | Progress: (8/20) | 7.65 s
[Task 17/25] Current/Best: 17.82/ 22.95 GFLOPS | Progress: (12/20) | 9.73 s
[Task 17/25] Current/Best: 16.49/ 22.95 GFLOPS | Progress: (16/20) | 11.86 s
[Task 17/25] Current/Best: 10.03/ 22.95 GFLOPS | Progress: (20/20) | 14.00 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.20/ 18.00 GFLOPS | Progress: (4/20) | 3.75 s
[Task 18/25] Current/Best: 10.60/ 18.99 GFLOPS | Progress: (8/20) | 7.18 s
[Task 18/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (12/20) | 9.12 s
[Task 18/25] Current/Best: 10.11/ 19.12 GFLOPS | Progress: (16/20) | 12.68 s
[Task 18/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (20/20) | 14.21 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.14/ 20.28 GFLOPS | Progress: (4/20) | 6.12 s
[Task 19/25] Current/Best: 2.60/ 20.28 GFLOPS | Progress: (8/20) | 9.39 s
[Task 19/25] Current/Best: 18.76/ 21.34 GFLOPS | Progress: (12/20) | 12.16 s
[Task 19/25] Current/Best: 15.08/ 21.34 GFLOPS | Progress: (16/20) | 15.01 s
[Task 19/25] Current/Best: 2.70/ 23.17 GFLOPS | Progress: (20/20) | 17.79 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.31/ 14.86 GFLOPS | Progress: (4/20) | 3.37 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.51/ 17.51 GFLOPS | Progress: (4/20) | 6.36 s
[Task 1/25] Current/Best: 6.16/ 17.51 GFLOPS | Progress: (8/20) | 9.33 s
[Task 1/25] Current/Best: 11.51/ 22.80 GFLOPS | Progress: (12/20) | 11.76 s
[Task 1/25] Current/Best: 16.82/ 22.83 GFLOPS | Progress: (16/20) | 13.45 s
[Task 1/25] Current/Best: 11.60/ 23.91 GFLOPS | Progress: (20/20) | 15.19 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/ 12.87 GFLOPS | Progress: (4/20) | 3.71 s
[Task 2/25] Current/Best: 14.17/ 17.58 GFLOPS | Progress: (8/20) | 5.04 s
[Task 2/25] Current/Best: 21.26/ 21.26 GFLOPS | Progress: (12/20) | 6.37 s
[Task 2/25] Current/Best: 12.24/ 21.26 GFLOPS | Progress: (16/20) | 7.63 s
[Task 2/25] Current/Best: 18.84/ 21.26 GFLOPS | Progress: (20/20) | 9.20 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/ 10.56 GFLOPS | Progress: (4/20) | 5.90 s
[Task 3/25] Current/Best: 15.55/ 16.86 GFLOPS | Progress: (8/20) | 7.82 s
[Task 3/25] Current/Best: 14.92/ 16.86 GFLOPS | Progress: (12/20) | 9.55 s
[Task 3/25] Current/Best: 7.06/ 23.86 GFLOPS | Progress: (16/20) | 11.47 s
[Task 3/25] Current/Best: 12.59/ 23.86 GFLOPS | Progress: (20/20) | 16.15 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.50/ 18.16 GFLOPS | Progress: (4/20) | 2.45 s
[Task 4/25] Current/Best: 6.87/ 18.16 GFLOPS | Progress: (8/20) | 6.85 s
[Task 4/25] Current/Best: 21.67/ 21.67 GFLOPS | Progress: (12/20) | 11.35 s
[Task 4/25] Current/Best: 16.75/ 21.67 GFLOPS | Progress: (16/20) | 13.60 s
[Task 4/25] Current/Best: 13.33/ 21.67 GFLOPS | Progress: (20/20) | 15.58 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.28/ 10.15 GFLOPS | Progress: (4/20) | 2.61 s
[Task 5/25] Current/Best: 11.57/ 12.59 GFLOPS | Progress: (8/20) | 4.71 s
[Task 5/25] Current/Best: 11.58/ 18.11 GFLOPS | Progress: (12/20) | 7.84 s
[Task 5/25] Current/Best: 11.50/ 22.53 GFLOPS | Progress: (16/20) | 9.31 s
[Task 5/25] Current/Best: 11.99/ 22.53 GFLOPS | Progress: (20/20) | 11.17 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.26/ 20.70 GFLOPS | Progress: (4/20) | 4.02 s
[Task 6/25] Current/Best: 18.91/ 20.70 GFLOPS | Progress: (8/20) | 5.79 s
[Task 6/25] Current/Best: 13.31/ 20.70 GFLOPS | Progress: (12/20) | 7.73 s
[Task 6/25] Current/Best: 19.70/ 20.70 GFLOPS | Progress: (16/20) | 10.00 s
[Task 6/25] Current/Best: 3.72/ 20.70 GFLOPS | Progress: (20/20) | 12.52 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.22/ 12.90 GFLOPS | Progress: (4/20) | 3.63 s
[Task 7/25] Current/Best: 20.20/ 20.75 GFLOPS | Progress: (8/20) | 5.16 s
[Task 7/25] Current/Best: 16.03/ 20.75 GFLOPS | Progress: (12/20) | 7.07 s
[Task 7/25] Current/Best: 12.24/ 20.81 GFLOPS | Progress: (16/20) | 9.12 s
[Task 7/25] Current/Best: 6.30/ 21.72 GFLOPS | Progress: (20/20) | 11.58 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.64/ 14.54 GFLOPS | Progress: (4/20) | 2.97 s
[Task 8/25] Current/Best: 9.56/ 14.54 GFLOPS | Progress: (8/20) | 7.70 s
[Task 8/25] Current/Best: 12.60/ 14.54 GFLOPS | Progress: (12/20) | 13.93 s
[Task 8/25] Current/Best: 18.73/ 18.73 GFLOPS | Progress: (16/20) | 16.05 s
[Task 8/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (20/20) | 22.57 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.38/ 15.79 GFLOPS | Progress: (4/20) | 12.00 s
[Task 9/25] Current/Best: 23.39/ 23.39 GFLOPS | Progress: (8/20) | 13.81 s
[Task 9/25] Current/Best: 8.24/ 23.39 GFLOPS | Progress: (12/20) | 16.21 s
[Task 9/25] Current/Best: 18.01/ 23.39 GFLOPS | Progress: (16/20) | 18.89 s
[Task 9/25] Current/Best: 9.21/ 23.39 GFLOPS | Progress: (20/20) | 26.48 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.24/ 18.24 GFLOPS | Progress: (4/20) | 2.61 s
[Task 10/25] Current/Best: 15.55/ 18.24 GFLOPS | Progress: (8/20) | 4.20 s
[Task 10/25] Current/Best: 11.24/ 18.86 GFLOPS | Progress: (12/20) | 5.74 s
[Task 10/25] Current/Best: 19.13/ 20.24 GFLOPS | Progress: (16/20) | 6.84 s
[Task 10/25] Current/Best: 8.88/ 20.24 GFLOPS | Progress: (20/20
) | 8.38 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.21/ 18.17 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 16.32/ 18.17 GFLOPS | Progress: (8/20) | 6.08 s
[Task 11/25] Current/Best: 18.00/ 18.17 GFLOPS | Progress: (12/20) | 8.10 s
[Task 11/25] Current/Best: 13.48/ 21.19 GFLOPS | Progress: (16/20) | 10.89 s
[Task 11/25] Current/Best: 19.45/ 21.59 GFLOPS | Progress: (20/20) | 12.93 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.82/ 18.10 GFLOPS | Progress: (4/20) | 5.37 s
[Task 12/25] Current/Best: 5.23/ 18.10 GFLOPS | Progress: (8/20) | 9.09 s
[Task 12/25] Current/Best: 18.71/ 18.75 GFLOPS | Progress: (12/20) | 11.10 s
[Task 12/25] Current/Best: 15.28/ 18.75 GFLOPS | Progress: (16/20) | 13.90 s
[Task 12/25] Current/Best: 15.09/ 18.75 GFLOPS | Progress: (20/20) | 15.84 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.61/ 17.31 GFLOPS | Progress: (4/20) | 3.71 s
[Task 13/25] Current/Best: 16.11/ 20.78 GFLOPS | Progress: (8/20) | 6.14 s
[Task 13/25] Current/Best: 19.54/ 21.39 GFLOPS | Progress: (12/20) | 9.10 s
[Task 13/25] Current/Best: 12.25/ 21.39 GFLOPS | Progress: (16/20) | 12.48 s
[Task 13/25] Current/Best: 18.42/ 21.39 GFLOPS | Progress: (20/20) | 14.76 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.56/ 13.56 GFLOPS | Progress: (4/20) | 3.28 s
[Task 14/25] Current/Best: 6.08/ 13.56 GFLOPS | Progress: (8/20) | 5.49 s
[Task 14/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (12/20) | 8.06 s
[Task 14/25] Current/Best: 15.88/ 19.95 GFLOPS | Progress: (16/20) | 9.72 s Done.
+
[Task 14/25] Current/Best: 17.23/ 19.95 GFLOPS | Progress: (20/20) | 11.49 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.19/ 17.65 GFLOPS | Progress: (4/20) | 2.75 s
[Task 15/25] Current/Best: 14.44/ 18.07 GFLOPS | Progress: (8/20) | 4.09 s
[Task 15/25] Current/Best: 10.39/ 22.30 GFLOPS | Progress: (12/20) | 6.16 s
[Task 15/25] Current/Best: 20.38/ 22.30 GFLOPS | Progress: (16/20) | 9.15 s
[Task 15/25] Current/Best: 9.53/ 22.30 GFLOPS | Progress: (20/20) | 10.13 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (4/20) | 2.99 s
[Task 16/25] Current/Best: 3.04/ 20.63 GFLOPS | Progress: (8/20) | 4.60 s
[Task 16/25] Current/Best: 19.56/ 20.63 GFLOPS | Progress: (12/20) | 5.83 s
[Task 16/25] Current/Best: 17.37/ 20.63 GFLOPS | Progress: (16/20) |
7.20 s
[Task 16/25] Current/Best: 10.02/ 21.51 GFLOPS | Progress: (20/20) | 9.25 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.34/ 18.77 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 13.99/ 23.02 GFLOPS | Progress: (8/20) | 7.60 s
[Task 17/25] Current/Best: 17.20/ 23.02 GFLOPS | Progress: (12/20) | 9.65 s
[Task 17/25] Current/Best: 16.57/ 23.02 GFLOPS | Progress: (16/20) | 11.79 s
[Task 17/25] Current/Best: 10.04/ 23.02 GFLOPS | Progress: (20/20) | 13.92 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.19/ 17.69 GFLOPS | Progress: (4/20) | 3.73 s
[Task 18/25] Current/Best: 10.58/ 19.99 GFLOPS | Progress: (8/20) | 7.25 s
[Task 18/25] Current/Best: 19.31/ 19.99 GFLOPS | Progress: (12/20) | 9.18 s
[Task 18/25] Current/Best: 10.14/ 19.99 GFLOPS | Progress: (16/20) | 12.79 s
[Task 18/25] Current/Best: 20.45/ 20.45 GFLOPS | Progress: (20/20) | 14.30 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.20/ 20.41 GFLOPS | Progress: (4/20) | 6.12 s
[Task 19/25] Current/Best: 2.60/ 20.41 GFLOPS | Progress: (8/20) | 9.40 s
[Task 19/25] Current/Best: 20.40/ 21.56 GFLOPS | Progress: (12/20) | 12.29 s
[Task 19/25] Current/Best: 14.86/ 21.67 GFLOPS | Progress: (16/20) | 15.09 s
[Task 19/25] Current/Best: 2.69/ 23.39 GFLOPS | Progress: (20/20) | 17.94 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.43/ 15.16 GFLOPS | Progress: (4/20) | 3.34 s Done.
Done.
-
[Task 20/25] Current/Best: 10.04/ 14.86 GFLOPS | Progress: (8/20) | 6.87 s
[Task 20/25] Current/Best: 2.32/ 16.60 GFLOPS | Progress: (12/20) | 10.84 s
[Task 20/25] Current/Best: 12.41/ 16.60 GFLOPS | Progress: (16/20) | 14.63 s
[Task 20/25] Current/Best: 13.00/ 21.85 GFLOPS | Progress: (20/20) | 16.73 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.68 GFLOPS | Progress: (4/20) | 3.27 s
[Task 21/25] Current/Best: 14.45/ 17.68 GFLOPS | Progress: (8/20) | 4.86 s
[Task 21/25] Current/Best: 1.61/ 17.68 GFLOPS | Progress: (12/20) | 7.03 s
[Task 21/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (16/20) | 10.56 s
[Task 21/25] Current/Best: 4.45/ 17.93 GFLOPS | Progress: (20/20) | 17.86 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.80 GFLOPS | Progress: (4/20
) | 2.77 s
[Task 22/25] Current/Best: 9.16/ 21.15 GFLOPS | Progress: (8/20) | 4.77 s
[Task 22/25] Current/Best: 19.67/ 21.15 GFLOPS | Progress: (12/20) | 7.13 s
[Task 22/25] Current/Best: 14.96/ 21.15 GFLOPS | Progress: (16/20) | 9.19 s
[Task 22/25] Current/Best: 14.34/ 21.15 GFLOPS | Progress: (20/20) | 10.88 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.30/ 20.27 GFLOPS | Progress: (4/20) | 3.29 s
[Task 23/25] Current/Best: 15.84/ 20.27 GFLOPS | Progress: (8/20) | 6.67 s
[Task 23/25] Current/Best: 20.89/ 21.42 GFLOPS | Progress: (12/20) | 8.52 s
[Task 23/25] Current/Best: 6.37/ 21.42 GFLOPS | Progress: (16/20) | 15.65 s
[Task 23/25] Current/Best: 7.78/ 21.42 GFLOPS | Progress: (20/20) | 19.90 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.44/ 8.44 GFLOPS | Progress: (4/20) | 11.86 s
[Task 24/25] Current/Best: 3.39/ 8.44 GFLOPS | Progress: (8/20) | 23.14 s
[Task 24/25] Current/Best: 4.56/ 8.44 GFLOPS | Progress: (12/20) | 33.88 s Done.
-
[Task 24/25] Current/Best: 6.19/ 8.57 GFLOPS | Progress: (16/20) | 39.33 s
[Task 24/25] Current/Best: 3.36/ 8.87 GFLOPS | Progress: (20/20) | 45.33 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) | 11.63 s
[Task 25/25] Current/Best: 5.65/ 7.73 GFLOPS | Progress: (8/20) | 22.92 s
[Task 25/25] Current/Best: 5.66/ 7.73 GFLOPS | Progress: (12/20) | 34.26 s
[Task 25/25] Current/Best: 5.66/ 9.05 GFLOPS | Progress: (16/20) | 36.04 s
[Task 25/25] Current/Best: 2.93/ 9.05 GFLOPS | Progress: (20/20) | 46.71 s
+
[Task 20/25] Current/Best: 10.14/ 15.16 GFLOPS | Progress: (8/20) | 6.81 s
[Task 20/25] Current/Best: 2.33/ 16.76 GFLOPS | Progress: (12/20) | 10.74 s
[Task 20/25] Current/Best: 12.27/ 16.76 GFLOPS | Progress: (16/20) | 14.35 s
[Task 20/25] Current/Best: 13.22/ 22.04 GFLOPS | Progress: (20/20) | 16.44 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.50 GFLOPS | Progress: (4/20) | 3.25 s
[Task 21/25] Current/Best: 14.62/ 17.50 GFLOPS | Progress: (8/20) | 4.83 s
[Task 21/25] Current/Best: 1.61/ 17.50 GFLOPS | Progress: (12/20) | 7.02 s
[Task 21/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (16/20) | 10.49 s
[Task 21/25] Current/Best: 4.47/ 17.93 GFLOPS | Progress: (20/20) | 17.62 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.99 GFLOPS | Progress: (4/20
) | 2.71 s
[Task 22/25] Current/Best: 9.18/ 21.60 GFLOPS | Progress: (8/20) | 4.68 s
[Task 22/25] Current/Best: 19.89/ 21.60 GFLOPS | Progress: (12/20) | 7.00 s
[Task 22/25] Current/Best: 14.95/ 21.60 GFLOPS | Progress: (16/20) | 9.06 s
[Task 22/25] Current/Best: 14.64/ 21.60 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: 17.46/ 20.73 GFLOPS | Progress: (4/20) | 3.29 s
[Task 23/25] Current/Best: 15.40/ 20.73 GFLOPS | Progress: (8/20) | 6.68 s
[Task 23/25] Current/Best: 21.03/ 21.65 GFLOPS | Progress: (12/20) | 8.49 s
[Task 23/25] Current/Best: 6.43/ 21.65 GFLOPS | Progress: (16/20) | 15.58 s
[Task 23/25] Current/Best: 7.93/ 21.65 GFLOPS | Progress: (20/20) | 19.82 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.00/ 8.00 GFLOPS | Progress: (4/20) | 11.82 s
[Task 24/25] Current/Best: 2.11/ 8.00 GFLOPS | Progress: (8/20) | 22.85 s
[Task 24/25] Current/Best: 4.45/ 8.00 GFLOPS | Progress: (12/20) | 34.40 s Done.
+
[Task 24/25] Current/Best: 6.66/ 8.71 GFLOPS | Progress: (16/20) | 39.82 s
[Task 24/25] Current/Best: 3.27/ 8.96 GFLOPS | Progress: (20/20) | 45.94 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/ 2.76 GFLOPS | Progress: (4/20) | 11.63 s
[Task 25/25] Current/Best: 5.86/ 7.93 GFLOPS | Progress: (8/20) | 22.92 s
[Task 25/25] Current/Best: 5.67/ 7.93 GFLOPS | Progress: (12/20) | 34.44 s
[Task 25/25] Current/Best: 5.85/ 8.41 GFLOPS | Progress: (16/20) | 36.29 s
[Task 25/25] Current/Best: 2.81/ 8.73 GFLOPS | Progress: (20/20) | 47.01 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 413.2521597000027, 'median': 413.27946029999794, 'std': 0.9055579209214949}
- unoptimized: {'mean': 496.84622677000107, 'median': 496.8420989500032, 'std': 1.0463698614272814}
+ optimized: {'mean': 408.7253329400005, 'median': 408.8333002500008, 'std': 0.6349661879927168}
+ unoptimized: {'mean': 497.57861620000085, 'median': 497.59652024999923, 'std': 0.3718688564612551}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 24.053 seconds)
+ **Total running time of the script:** ( 10 minutes 18.784 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 47962226a..a9c12d6d2 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
- 1.272e-07 secs/op
+ 1.266e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 46aea2036..e9e7f48cd 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, 0x23a9e830)), stage(b, placeholder(b, 0x218e12a0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x1ae3b3d0)), stage(b, placeholder(b, 0x214da950)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index c0e113059..9bda5cf2d 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**13:37.529** total execution time for **tutorial** files:
+**13:04.866** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:24.053 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:18.784 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:14.897 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.500 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.583 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:46.471 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.085 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.984 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.812 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.236 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.229 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.035 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.706 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.704 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.157 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.144 | 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``) | 00:00.002 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index de5792980..150a641d7 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,8 +301,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
- naive: 0.000008
+ Numpy running time: 0.000008
+ naive: 0.000006
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py: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. "
- parallel: 0.000008
+ parallel: 0.000007
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.816699999490083e-06 1.0
- naive 7.6169e-06 1.1173881791144946
- parallel 8.19e-06 1.2014611176394216
- vector 2.4622499999999997e-05 3.6120850267492863
+ numpy 8.094889999483712e-06 1.0
+ naive 5.8407e-06 0.7215292610983617
+ parallel 7.087599999999999e-06 0.875564708161821
+ vector 2.46333e-05 3.043067910937777
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019723
+ Numpy running time: 0.018535
@@ -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: 3.364989
+ none: 3.531342
@@ -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: 0.300650
+ blocking: 0.298599
@@ -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: 0.337639
+ vectorization: 0.336347
@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: 0.117698
+ loop permutation: 0.117793
@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: 0.110052
+ array packing: 0.110395
@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: 0.110667
+ block caching: 0.111298
@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: 0.145049
+ parallelization: 0.145169
@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 3.3649892858 1.0
- blocking 0.300649999 0.08934649517866824
- vectorization 0.33763905850000003 0.10033882126306057
- loop permutation 0.117697766 0.03497715921315876
- array packing 0.11005166200000001 0.03270490710458119
- block caching 0.1106668524 0.032887728013579635
- parallelization 0.1450493464 0.043105440784640014
+ none 3.5313423024999997 1.0
+ blocking 0.2985993607 0.08455690078206458
+ vectorization 0.3363466034 0.09524610603788955
+ loop permutation 0.1177926255 0.033356331788229415
+ array packing 0.1103945744 0.03126136322775807
+ block caching 0.11129787839999998 0.03151715944421675
+ parallelization 0.1451688418 0.041108685979614125
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.583 seconds)
+ **Total running time of the script:** ( 1 minutes 2.500 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 534c4db19..7a459ad5c 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-b0b9bd976ba14cfc8b224396ab065ff03a34f46a
+c9a350c800809d9431c8b2b427e8f5af10a3ee89
diff --git a/docs/contribute/code_guide.html b/docs/contribute/code_guide.html
index 3086519a5..1441a2538 100644
--- a/docs/contribute/code_guide.html
+++ b/docs/contribute/code_guide.html
@@ -467,11 +467,13 @@ distinction. See further discussion <cite>here
server can go down or be slow), so try to avoid using the network at all during tests. In some cases
this isn’t a reasonable proposition (e.g. the docs tutorials which need to download models).</p>
<p>In these cases you can re-host files in S3 for fast access in CI. A committer can upload a file,
-specified by a name, hash, and path in S3, using the <cite>workflow_dispatch</cite> event on <a class="reference external" href="https://github.com/apache/tvm/actions/workflows/upload_ci_resource.yml">the
+specified by a name, hash, and path in S3, using the <code class="docutils literal notranslate"><span class="pre">workflow_dispatch</span></code> event on <a class="reference external" href="https://github.com/apache/tvm/actions/workflows/upload_ci_resource.yml">the
upload_ci_resource.yml GitHub Actions workflow</a>. The sha256 must match
the file or it will not be uploaded. The upload path is user-defined so it can be any path (no
trailing or leading slashes allowed) but be careful not to collide with existing resources on
-accident.</p>
+accident. Once uploaded you should send a PR to update the <code class="docutils literal notranslate"><span class="pre">URL_MAP</span></code> in
+<a class="reference external" href="https://github.com/apache/tvm/blob/main/tests/scripts/request_hook/request_hook.py">request_hook.py</a>
+with the new URL.</p>
</div>
<div class="section" id="handle-integer-constant-expression">
<h2><a class="toc-backref" href="#id5">Handle Integer Constant Expression</a><a class="headerlink" href="#handle-integer-constant-expression" title="Permalink to this headline">¶</a></h2>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index f13ff0961..2341d0bd4 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 6.100 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.889 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 7ea3a5a6e..b5c6ebc6a 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.zip00637364-3d26-453a-9826-34800b4484bb 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.zip1bf5a0df-0d32-4f0b-a514-37dd0e126b40 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 9bace2e98..f41b69a40 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,16 +432,13 @@ 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, 55.3MB/s]
- 28%|##7 | 11.6M/41.5M [00:00<00:00, 34.8MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 27.7MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.0MB/s]
- 61%|######1 | 25.5M/41.5M [00:00<00:00, 29.2MB/s]
- 68%|######8 | 28.3M/41.5M [00:00<00:00, 28.1MB/s]
- 77%|#######7 | 32.1M/41.5M [00:01<00:00, 30.3MB/s]
- 85%|########4 | 35.1M/41.5M [00:01<00:00, 28.4MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 21.2MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 27.8MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 37.9MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 41.6MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 38.1MB/s]
+ 63%|######2 | 26.0M/41.5M [00:00<00:00, 35.3MB/s]
+ 77%|#######7 | 32.1M/41.5M [00:00<00:00, 42.5MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 18.9MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 27.1MB/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 6cd4196ae..0136c06a3 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,12 @@ 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]
- 32%|###1 | 14.3M/44.7M [00:00<00:00, 150MB/s]
- 75%|#######4 | 33.3M/44.7M [00:00<00:00, 179MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 183MB/s]
+ 5%|5 | 2.29M/44.7M [00:00<00:01, 24.0MB/s]
+ 12%|#1 | 5.30M/44.7M [00:00<00:01, 28.4MB/s]
+ 35%|###5 | 15.8M/44.7M [00:00<00:00, 65.6MB/s]
+ 62%|######1 | 27.5M/44.7M [00:00<00:00, 88.0MB/s]
+ 88%|########7 | 39.2M/44.7M [00:00<00:00, 101MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 85.7MB/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 682bbd10d..7430c5ec0 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.820 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.152 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 0f882e0e2..380419d97 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>05:08.926</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:04.191</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>01:06.100</p></td>
+<td><p>01:04.889</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>01:02.820</p></td>
+<td><p>01:02.152</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>00:39.193</p></td>
+<td><p>00:38.684</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>00:28.761</p></td>
+<td><p>00:28.505</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>00:26.032</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:25.459</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>00:25.446</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>00:24.173</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>00:23.190</p></td>
+<td><p>00:22.631</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>00:19.466</p></td>
+<td><p>00:19.698</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>00:15.485</p></td>
+<td><p>00:15.566</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>00:02.432</p></td>
+<td><p>00:02.433</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 c2e39f9c1..0e1b80317 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)
- 16.1864 16.2044 16.3200 16.0568 0.0882
+ 15.8420 15.8727 16.1260 15.5095 0.2227
</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 395d7dd2e..41eb4af19 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,37 +436,21 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 3%|2 | 5.00M/170M [00:00<00:03, 52.4MB/s]
- 6%|5 | 10.0M/170M [00:00<00:03, 47.5MB/s]
- 9%|8 | 14.6M/170M [00:00<00:03, 47.0MB/s]
- 13%|#2 | 21.6M/170M [00:00<00:02, 56.6MB/s]
- 16%|#6 | 27.3M/170M [00:00<00:02, 57.2MB/s]
- 19%|#9 | 33.0M/170M [00:00<00:02, 58.0MB/s]
- 23%|##2 | 38.8M/170M [00:00<00:02, 58.7MB/s]
- 26%|##6 | 44.4M/170M [00:00<00:02, 53.2MB/s]
- 29%|##9 | 49.5M/170M [00:00<00:02, 50.1MB/s]
- 33%|###2 | 55.4M/170M [00:01<00:02, 53.4MB/s]
- 36%|###5 | 60.6M/170M [00:01<00:02, 49.5MB/s]
- 40%|###9 | 67.5M/170M [00:01<00:01, 55.6MB/s]
- 43%|####2 | 73.0M/170M [00:01<00:01, 54.7MB/s]
- 46%|####6 | 78.3M/170M [00:01<00:01, 54.7MB/s]
- 50%|####9 | 84.8M/170M [00:01<00:01, 58.6MB/s]
- 53%|#####3 | 90.5M/170M [00:01<00:01, 55.3MB/s]
- 56%|#####6 | 95.8M/170M [00:01<00:01, 52.9MB/s]
- 60%|#####9 | 101M/170M [00:01<00:01, 53.9MB/s]
- 63%|######3 | 107M/170M [00:02<00:01, 56.1MB/s]
- 66%|######6 | 112M/170M [00:02<00:01, 47.8MB/s]
- 69%|######9 | 117M/170M [00:02<00:01, 47.9MB/s]
- 72%|#######1 | 122M/170M [00:02<00:01, 42.7MB/s]
- 74%|#######4 | 126M/170M [00:02<00:01, 41.0MB/s]
- 78%|#######7 | 132M/170M [00:02<00:00, 46.0MB/s]
- 81%|########1 | 138M/170M [00:02<00:00, 49.2MB/s]
- 84%|########3 | 143M/170M [00:02<00:00, 47.2MB/s]
- 87%|########6 | 147M/170M [00:03<00:00, 47.4MB/s]
- 90%|########9 | 153M/170M [00:03<00:00, 50.5MB/s]
- 94%|#########3| 159M/170M [00:03<00:00, 54.8MB/s]
- 97%|#########7| 165M/170M [00:03<00:00, 57.1MB/s]
-100%|##########| 170M/170M [00:03<00:00, 52.0MB/s]
+ 3%|2 | 5.09M/170M [00:00<00:03, 53.1MB/s]
+ 10%|# | 17.6M/170M [00:00<00:01, 99.2MB/s]
+ 18%|#7 | 30.1M/170M [00:00<00:01, 113MB/s]
+ 25%|##5 | 42.5M/170M [00:00<00:01, 120MB/s]
+ 32%|###2 | 55.0M/170M [00:00<00:00, 124MB/s]
+ 40%|###9 | 67.1M/170M [00:00<00:00, 125MB/s]
+ 47%|####6 | 79.1M/170M [00:00<00:00, 107MB/s]
+ 54%|#####3 | 91.5M/170M [00:00<00:00, 113MB/s]
+ 61%|######1 | 104M/170M [00:00<00:00, 118MB/s]
+ 68%|######8 | 116M/170M [00:01<00:00, 121MB/s]
+ 76%|#######5 | 129M/170M [00:01<00:00, 124MB/s]
+ 83%|########2 | 141M/170M [00:01<00:00, 117MB/s]
+ 89%|########9 | 152M/170M [00:01<00:00, 99.2MB/s]
+ 97%|#########6| 164M/170M [00:01<00:00, 107MB/s]
+100%|##########| 170M/170M [00:01<00:00, 112MB/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').
@@ -561,7 +545,7 @@ 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 3.485 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 57.299 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 a39381cbd..7ee88b487 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,8 +480,9 @@ 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]
- 68%|######8 | 9.24M/13.6M [00:00<00:00, 96.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 113MB/s]
+ 35%|###5 | 4.77M/13.6M [00:00<00:00, 50.0MB/s]
+ 89%|########8 | 12.0M/13.6M [00:00<00:00, 65.2MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 61.6MB/s]
</pre></div>
</div>
</div>
@@ -570,7 +571,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4686 90.3536 93.4703 90.1925 0.3830
+ 90.3640 90.3067 91.7346 90.1768 0.2275
</pre></div>
</div>
<div class="admonition note">
@@ -609,7 +610,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.000 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.145 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 1e6a8f639..fbf1a604c 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.7657 120.7669 123.5156 120.0525 0.4338
+ 119.5618 119.5291 122.5479 118.8665 0.4038
</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 56.169 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.807 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 fd8917484..2da3b8e69 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 45.480 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 49.569 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 2731fc1b8..ad16c9f6e 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,27 +441,26 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 2%|1 | 2225/132723 [00:00<00:05, 22050.46KB/s]
- 4%|4 | 5813/132723 [00:00<00:04, 29847.11KB/s]
- 8%|8 | 10773/132723 [00:00<00:03, 38691.79KB/s]
- 13%|#3 | 17267/132723 [00:00<00:02, 48987.22KB/s]
- 18%|#8 | 24395/132723 [00:00<00:01, 56992.05KB/s]
- 24%|##3 | 31736/132723 [00:00<00:01, 62557.74KB/s]
- 29%|##9 | 38897/132723 [00:00<00:01, 65510.47KB/s]
- 35%|###4 | 46153/132723 [00:00<00:01, 67750.61KB/s]
- 40%|###9 | 52932/132723 [00:00<00:01, 57606.22KB/s]
- 45%|####5 | 60290/132723 [00:01<00:01, 61998.02KB/s]
- 51%|##### | 67518/132723 [00:01<00:01, 64896.39KB/s]
- 56%|#####6 | 74732/132723 [00:01<00:00, 66974.63KB/s]
- 62%|######1 | 81988/132723 [00:01<00:00, 68597.63KB/s]
- 67%|######7 | 89232/132723 [00:01<00:00, 69719.44KB/s]
- 73%|#######2 | 96543/132723 [00:01<00:00, 70717.84KB/s]
- 78%|#######8 | 104029/132723 [00:01<00:00, 71945.61KB/s]
- 84%|########3 | 111313/132723 [00:01<00:00, 72207.93KB/s]
- 89%|########9 | 118563/132723 [00:01<00:00, 57103.08KB/s]
- 95%|#########4| 125920/132723 [00:02<00:00, 61250.36KB/s]
-100%|#########9| 132484/132723 [00:02<00:00, 28601.67KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 51028.58KB/s]
+ 2%|1 | 2449/132723 [00:00<00:05, 24487.75KB/s]
+ 7%|6 | 8772/132723 [00:00<00:02, 47272.96KB/s]
+ 10%|# | 13500/132723 [00:00<00:02, 45289.65KB/s]
+ 14%|#4 | 18967/132723 [00:00<00:02, 48895.19KB/s]
+ 20%|#9 | 26381/132723 [00:00<00:01, 57825.33KB/s]
+ 25%|##5 | 33584/132723 [00:00<00:01, 62598.04KB/s]
+ 31%|### | 40865/132723 [00:00<00:01, 65906.74KB/s]
+ 36%|###6 | 48228/132723 [00:00<00:01, 68349.93KB/s]
+ 42%|####1 | 55573/132723 [00:00<00:01, 69934.82KB/s]
+ 47%|####7 | 62935/132723 [00:01<00:00, 71067.35KB/s]
+ 53%|#####2 | 70326/132723 [00:01<00:00, 71934.75KB/s]
+ 59%|#####8 | 77719/132723 [00:01<00:00, 72538.61KB/s]
+ 64%|######4 | 85053/132723 [00:01<00:00, 72775.72KB/s]
+ 70%|######9 | 92469/132723 [00:01<00:00, 73190.62KB/s]
+ 75%|#######5 | 99867/132723 [00:01<00:00, 73426.88KB/s]
+ 81%|######## | 107280/132723 [00:01<00:00, 73635.51KB/s]
+ 86%|########6 | 114700/132723 [00:01<00:00, 73802.89KB/s]
+ 92%|#########1| 122081/132723 [00:01<00:00, 73738.13KB/s]
+ 98%|#########7| 129493/132723 [00:01<00:00, 73851.17KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 67933.20KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -504,7 +503,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 39.036 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 38.755 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 5b84a6b28..132ae72f2 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>11:49.453</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:42.456</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</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>03:03.485</p></td>
+<td><p>02:57.299</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>02:39.036</p></td>
+<td><p>02:38.755</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>01:56.169</p></td>
+<td><p>01:52.807</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>01:45.480</p></td>
+<td><p>01:49.569</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:10.000</p></td>
+<td><p>01:09.145</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>00:30.446</p></td>
+<td><p>00:30.283</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>00:22.641</p></td>
+<td><p>00:22.567</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>00:22.189</p></td>
+<td><p>00:22.026</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 2786543cb..85a903ee0 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.zip9f311937-81e4-4c8b-849a-0f708fe9d0fe 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.zip074202f6-18bf-4cda-8d4c-6a1f12011b63 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 9f676cc4f..6203abeb8 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:42.021</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.950</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:38.745</p></td>
+<td><p>00:37.754</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>00:02.291</p></td>
+<td><p>00:02.238</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>00:00.977</p></td>
+<td><p>00:00.950</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 85c3a3868..12452f959 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: 6949us [6949us] (45.86%; 45.86%)
-FoldScaleAxis: 8202us [6us] (54.14%; 54.14%)
- FoldConstant: 8196us [1712us] (54.10%; 99.92%)
- InferType: 6484us [6484us] (42.80%; 79.12%)
+InferType: 6779us [6779us] (46.18%; 46.18%)
+FoldScaleAxis: 7900us [5us] (53.82%; 53.82%)
+ FoldConstant: 7895us [1675us] (53.78%; 99.93%)
+ InferType: 6220us [6220us] (42.37%; 78.78%)
</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: 6484us [6484us] (44.32%; 44.32%)
-FoldScaleAxis: 8145us [5us] (55.68%; 55.68%)
- FoldConstant: 8140us [1720us] (55.64%; 99.94%)
- InferType: 6420us [6420us] (43.89%; 78.87%)
+InferType: 6345us [6345us] (44.36%; 44.36%)
+FoldScaleAxis: 7959us [4us] (55.64%; 55.64%)
+ FoldConstant: 7955us [1647us] (55.61%; 99.95%)
+ InferType: 6308us [6308us] (44.10%; 79.30%)
</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 2d2bd9b68..c323fbec3 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: 40.230610 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.186297 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 2b8aebca1..3bd8371f9 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: 7.084874 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.916246 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 19cc85ca2..c010bde25 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: 0.019386
-Baseline: 3.389477
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018752
+Baseline: 3.545060
</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: 0.305083
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.302708
</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: 0.340637
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.329779
</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: 0.116883
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117075
</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: 0.111949
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111664
</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: 0.111673
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112647
</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: 0.145606
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145529
</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 841739d51..60285f36a 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>00:34.582</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.799</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>00:32.382</p></td>
+<td><p>00:32.615</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>00:01.217</p></td>
+<td><p>00:01.198</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:00.984</p></td>
+<td><p>00:00.986</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 03c3c9a34..79502c5bc 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>06:10.051</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:23.310</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>03:22.661</p></td>
+<td><p>03:25.189</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>01:23.419</p></td>
+<td><p>01:22.797</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>00:47.363</p></td>
+<td><p>00:47.024</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>00:18.596</p></td>
+<td><p>00:30.482</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:09.098</p></td>
+<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>00:08.991</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.915</p></td>
+<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>00:08.827</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 f0fe7851d..2ce9ee85b 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,268 +491,72 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- 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
- conv2d_nchw_1[14] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[3] = 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[15] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- let cse_var_1: int32 = (rc.outer.outer*1568)
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [1]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [108]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_1: int32 = (rc.outer.outer*36)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 343), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 19), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 441), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 539), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 70), 81)) && (floormod((threadIdx.x_1 + 70), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 637), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 38), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 38), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 735)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 735), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 833), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 40), 81)) && (floormod((threadIdx.x_1 + 40), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 931), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 40), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 57), 81)) && (floormod((threadIdx.x_1 + 57), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1029), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 57), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else((((threadIdx.x_1 < 47) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @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_1 + (floordiv((threadIdx.x_1 + 1127), 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_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1225), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @tir.if_then_else((((threadIdx.x_1 < 45) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1323), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 3)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1372), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 44), 81)) && (floormod((threadIdx.x_1 + 44), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1421), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 44), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1470), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 61), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1519), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 61), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else((((threadIdx.x_1 < 43) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 78), 81)) && (floormod((threadIdx.x_1 + 78), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1617), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 78), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 46), 81)) && (floormod((threadIdx.x_1 + 46), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1666), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 46), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 5), 9)) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1715), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 14), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 7), 9)) && (floormod((threadIdx.x_1 + 63), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1764), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 7), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @tir.if_then_else((((threadIdx.x_1 < 41) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1813), 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" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1862), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 48), 81)) && (floormod((threadIdx.x_1 + 48), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1911), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2009)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 65), 81)) && (floormod((threadIdx.x_1 + 65), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2009), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 33), 81)) && (floormod((threadIdx.x_1 + 33), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2058), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 33), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2107)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 1), 81)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2107), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 50), 81)) && (floormod((threadIdx.x_1 + 50), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2156), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 50), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2205)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2205), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2254), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2303)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 35), 81)) && (floormod((threadIdx.x_1 + 35), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2303), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 35), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2401)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 52), 81)) && (floormod((threadIdx.x_1 + 52), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2401), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 52), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2450), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 2499)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 69), 81)) && (floormod((threadIdx.x_1 + 69), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2499), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 69), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2548), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_1 < 108), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7) [...]
}
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 4) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24))] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + (threadIdx.x_2*8)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer* [...]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 1)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + (threadIdx.x_2*8)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 2)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + (threadIdx.x_2*8)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 4)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 5)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 7)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 8)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 10)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 11)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 13)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 14)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 16)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 17)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 19)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 20)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + (threadIdx.x_2*2)), 3)*3)) + 2)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3))]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 22)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2) < 192), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*1176) + (threadIdx.x_2*24)) + 23)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*49) + threadIdx.x_2), 12)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + (threadIdx.x_2*8)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*98) + (threadIdx.x_2*2)) + 1), 3)*3)) + 2)]
- }
- }
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ry.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 8) {
- let cse_var_9: int32 = (ff.outer.inner + 8)
- let cse_var_8: int32 = (ff.outer.inner + 6)
- let cse_var_7: int32 = (ff.outer.inner + 4)
- let cse_var_6: int32 = (ff.outer.inner + 2)
- let cse_var_5: int32 = (ff.outer.inner + 14)
- let cse_var_4: int32 = (ff.outer.inner + 12)
- let cse_var_3: int32 = (ff.outer.inner + 10)
- let cse_var_2: int32 = ((((ff.outer.inner*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3))
- {
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_2]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 576)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1152)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1728)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 2304)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 2880)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 3456)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 4032)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 577)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1153)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1729)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 2305)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 2881)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 3457)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 4033)]))
- conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 578)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1154)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1730)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2306)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2882)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 3458)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (floordiv(threadIdx.x, 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 4034)]))
- }
- }
- }
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 36)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
}
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 30)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 31)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 32)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 33)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 34)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 57)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 58)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 59)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 60)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 61)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 62)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + 35)]))
}
}
- for (i1.inner: int32, 0, 2) {
- compute[(((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*16) + i1.inner)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*16) + i1.inner) + 2)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*16) + i1.inner) + 4)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 294)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*16) + i1.inner) + 6)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 392)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*16) + i1.inner) + 8)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 490)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*16) + i1.inner) + 10)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 588)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*16) + i1.inner) + 12)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 686)] = max((conv2d_nchw_1[(i1.inner + 14)] + bias[(((blockIdx.x*16) + i1.inner) + 14)]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
</pre></div>
@@ -788,7 +592,7 @@ 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: 0.388 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.406 ms
</pre></div>
</div>
</div>
@@ -818,35 +622,35 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_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=8)
+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=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=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)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=8)
+compute_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=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_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)
@@ -864,14 +668,14 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+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=49)
+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", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -891,201 +695,63 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[16];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[4608];
+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[1];
+ __shared__ float pad_temp_shared[108];
+ __shared__ float kernel_shared[1152];
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[14] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 441)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 637)] = (((((9 <= ((((int)threadIdx.x) + 70) % 81)) && (((((int)threadIdx.x) + 70) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 637) / 81) * 49)) + ((((((int)threadIdx.x) + 70) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 735)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 735) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 833)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 833) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((9 <= ((((int)threadIdx.x) + 40) % 81)) && (((((int)threadIdx.x) + 40) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 931) / 81) * 49)) + ((((((int)threadIdx.x) + 40) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((1 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 81) * 49)) + (((((int)threadIdx.x) + 8) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((9 <= ((((int)threadIdx.x) + 57) % 81)) && (((((int)threadIdx.x) + 57) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1029) / 81) * 49)) + ((((((int)threadIdx.x) + 57) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = ((((((int)threadIdx.x) < 47) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + (((((int)threadIdx.x) + 25) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1127) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1225) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((((int)threadIdx.x) < 45) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1323) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 13)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((9 <= ((((int)threadIdx.x) + 44) % 81)) && (((((int)threadIdx.x) + 44) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1421) / 81) * 49)) + ((((((int)threadIdx.x) + 44) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1519) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((((int)threadIdx.x) < 43) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + (((((int)threadIdx.x) + 29) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((9 <= ((((int)threadIdx.x) + 78) % 81)) && (((((int)threadIdx.x) + 78) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1617) / 81) * 49)) + ((((((int)threadIdx.x) + 78) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((9 <= ((((int)threadIdx.x) + 46) % 81)) && (((((int)threadIdx.x) + 46) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 81) * 49)) + ((((((int)threadIdx.x) + 46) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1715)] = (((1 <= ((((int)threadIdx.x) + 5) % 9)) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1715) / 81) * 49)) + (((((int)threadIdx.x) + 14) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) / 9) + 7) % 9)) && (((((int)threadIdx.x) + 63) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1764) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 7) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1813)] = ((((((int)threadIdx.x) < 41) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1813) / 81) * 49)) + (((((int)threadIdx.x) + 31) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1911) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + (((((int)threadIdx.x) + 16) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((9 <= ((((int)threadIdx.x) + 65) % 81)) && (((((int)threadIdx.x) + 65) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2009) / 81) * 49)) + ((((((int)threadIdx.x) + 65) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((9 <= ((((int)threadIdx.x) + 33) % 81)) && (((((int)threadIdx.x) + 33) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2058) / 81) * 49)) + ((((((int)threadIdx.x) + 33) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2107)] = ((((8 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2107) / 81) * 49)) + (((((int)threadIdx.x) + 1) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((9 <= ((((int)threadIdx.x) + 50) % 81)) && (((((int)threadIdx.x) + 50) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2156) / 81) * 49)) + ((((((int)threadIdx.x) + 50) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2205)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2205) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2254) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((9 <= ((((int)threadIdx.x) + 35) % 81)) && (((((int)threadIdx.x) + 35) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2303) / 81) * 49)) + ((((((int)threadIdx.x) + 35) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((6 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((((9 <= ((((int)threadIdx.x) + 52) % 81)) && (((((int)threadIdx.x) + 52) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2401) / 81) * 49)) + ((((((int)threadIdx.x) + 52) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2450) / 81) * 49)) + (((((int)threadIdx.x) + 20) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((9 <= ((((int)threadIdx.x) + 69) % 81)) && (((((int)threadIdx.x) + 69) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2499) / 81) * 49)) + ((((((int)threadIdx.x) + 69) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 44) {
- pad_temp_shared[(((int)threadIdx.x) + 2548)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2548) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 108) {
+ pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
}
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 4; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24))] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) * 8)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) * 8)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + (((int)threadIdx.x) * 8)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 4)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 5)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 7)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 8)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 10)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 11)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 13)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 14)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 16)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 17)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 2) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 19)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 20)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) * 2)) % 3) * 3)) + 2)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3))];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 22)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3)) + 1)];
- }
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) < 192) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 1176) + (((int)threadIdx.x) * 24)) + 23)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x)) / 12) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + (((int)threadIdx.x) * 8)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) * 2)) + 1) % 3) * 3)) + 2)];
- }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) / 3) + 8) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 576)]));
- conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1152)]));
- conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1728)]));
- conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2304)]));
- conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2880)]));
- conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 3456)]));
- conv2d_nchw[(ff_outer_inner + 14)] = (conv2d_nchw[(ff_outer_inner + 14)] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 4032)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 577)]));
- conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1153)]));
- conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1729)]));
- conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2305)]));
- conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2881)]));
- conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 3457)]));
- conv2d_nchw[(ff_outer_inner + 14)] = (conv2d_nchw[(ff_outer_inner + 14)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 4033)]));
- conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 578)]));
- conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1154)]));
- conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 1730)]));
- conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2306)]));
- conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 2882)]));
- conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 3458)]));
- conv2d_nchw[(ff_outer_inner + 14)] = (conv2d_nchw[(ff_outer_inner + 14)] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((ff_outer_inner * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + 4034)]));
- }
- }
- }
- }
- }
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 2)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 4)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 294)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 6)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 8)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 490)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 10)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 12)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 686)] = max((conv2d_nchw[(i1_inner + 14)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 14)]), 0.000000e+00f);
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 30)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 31)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 32)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 33)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 34)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 57)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 58)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 59)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 60)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 61)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 62)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
}
+ compute[((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -1121,7 +787,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 22.661 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 25.189 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 624705dee..6c7546f0d 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)
- 9.7872 9.7959 9.8087 9.7568 0.0221
+ 9.8802 9.8940 9.8976 9.8490 0.0221
</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 a98e7b21c..4cf41e323 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)
- 763.5554 761.6409 768.1319 760.8934 3.2504
+ 755.1005 753.8131 758.6839 752.8044 2.5671
</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 23.419 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.797 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 852a7c8a0..02b5b9e0f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,30 +625,103 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 1024) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ 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, 2) {
- for (i.inner.init: int32, 0, 2) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [64], [])[(((i.outer.inner*32) + (i.inner.init*16)) + j.init)] = 0f32
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = ((i.outer.inner*1024) + (i.inner.init*16))
+ {
+ 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
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 2) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*32) + (i.inner*16)) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*1024) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 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, 64) {
+ 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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (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*1024) + (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*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 4) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_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))
}
}
}
@@ -686,7 +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: 1.900 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.830 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 d45e70a6b..aa0b7fa73 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>00:46.124</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.490</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>00:46.089</p></td>
+<td><p>00:45.454</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>00:00.019</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 f5e1f3db6..e9ec84339 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: 175.34/175.34 result: MeasureResult(costs=(0.0013202865777777778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0665640830993652, timestamp=1660767589.506768) [('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: 0.00/175.34 result: Traceback (most recent call last):
+No: 9 GFLOPS: 174.79/174.79 result: MeasureResult(costs=(0.0013244358000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0026540756225586, timestamp=1660774528.6020384) [('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: 0.00/174.79 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.22/260.22 result: MeasureResult(costs=(0.000889643049723757,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7950384616851807, timestamp=1660767590.4355657) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.55/260.55 result: MeasureResult(costs=(0.0008885241325966852,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6772856712341309, timestamp=1660774529.5255716) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 5.45/260.22 result: MeasureResult(costs=(0.04244121325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8485305309295654, timestamp=1660767595.006558) [('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: 3.34/260.22 result: MeasureResult(costs=(0.069398374,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.563762187957764, timestamp=1660767596.242726) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.46/260.55 result: MeasureResult(costs=(0.04240317875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.854973316192627, timestamp=1660774534.1012974) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.35/260.55 result: MeasureResult(costs=(0.06914184450000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.570073127746582, timestamp=1660774535.3415718) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.22 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: 26.13/260.22 result: MeasureResult(costs=(0.008860859416666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1633820533752441, timestamp=1660767607.1559665) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+No: 18 GFLOPS: 26.02/260.55 result: MeasureResult(costs=(0.008896619916666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1460175514221191, timestamp=1660774546.2641227) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.22 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.55 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -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: 0.001276
+Time cost of this operator: 0.001251
</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 01d001708..ed93b739f 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 311.8 98.736 (1, 2, 10, 10, 3) 2 1 [311.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.019 0.956 (1, 6, 10, 10) 1 1 [3.019]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.308 (1, 1, 10, 10, 3) 1 1 [0.973]
-Total_time - 315.793 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.9 98.718 (1, 2, 10, 10, 3) 2 1 [311.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.089 0.978 (1, 6, 10, 10) 1 1 [3.089]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.305 (1, 1, 10, 10, 3) 1 1 [0.962]
+Total_time - 315.951 - - - - -
</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 79.312 96.686 (1, 6, 10, 10, 1) 2 1 [79.312]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.747 2.13 (1, 6, 10, 10) 1 1 [1.747]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 1.185 (1, 1, 10, 10, 3) 1 1 [0.972]
-Total_time - 82.031 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 89.75 97.007 (1, 6, 10, 10, 1) 2 1 [89.75]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.808 1.954 (1, 6, 10, 10) 1 1 [1.808]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 1.039 (1, 1, 10, 10, 3) 1 1 [0.961]
+Total_time - 92.519 - - - - -
</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 a80accd14..b1ead09a7 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/tmp066vjjuv/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpwd3j6wag/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/tmp066vjjuv/images/target contains 8144 images
-/tmp/tmp066vjjuv/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/tmpwd3j6wag/images/target contains 8144 images
+/tmp/tmpwd3j6wag/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 56s - loss: 0.2254 - accuracy: 0.9272 - val_loss: 0.1711 - val_accuracy: 0.9551
+328/328 - 55s - loss: 0.2443 - accuracy: 0.9176 - val_loss: 0.1523 - val_accuracy: 0.9547
Epoch 2/3
-328/328 - 53s - loss: 0.0985 - accuracy: 0.9619 - val_loss: 0.1269 - val_accuracy: 0.9611
+328/328 - 53s - loss: 0.0981 - accuracy: 0.9633 - val_loss: 0.1087 - val_accuracy: 0.9611
Epoch 3/3
-328/328 - 52s - loss: 0.0680 - accuracy: 0.9748 - val_loss: 0.1298 - val_accuracy: 0.9577
+328/328 - 52s - loss: 0.0716 - accuracy: 0.9723 - val_loss: 0.1413 - val_accuracy: 0.9490
-<keras.callbacks.History object at 0x7fb5f980e390>
+<keras.callbacks.History object at 0x7f193a00d590>
</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> ( 6 minutes 19.134 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 50.413 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 601133bae..603d5f21b 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>07:13.180</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:43.812</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>06:19.134</p></td>
+<td><p>05:50.413</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:42.664</p></td>
+<td><p>00:42.370</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>00:08.018</p></td>
+<td><p>00:07.737</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>00:03.363</p></td>
+<td><p>00:03.290</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 c9ffe2992..f23184623 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.378</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:42.698</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.738</p></td>
+<td><p>00:31.274</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.006</p></td>
+<td><p>00:09.850</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>00:01.628</p></td>
+<td><p>00:01.567</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 4cdc098c8..445dc5de6 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 0x7fb600c7a710>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f189e876c20>
</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 61c01a640..80411dc1b 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>00:04.140</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.075</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,23 +336,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.905</p></td>
+<td><p>00:01.874</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>00:00.989</p></td>
+<td><p>00:00.973</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.537</p></td>
+<td><p>00:00.529</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>00:00.522</p></td>
+<td><p>00:00.513</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>00:00.101</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 2c7786343..f95ef707f 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/tmpxlv58kt1/input0.cc'\nsource_filename = \"/tmp/tmpxlv58kt1/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/tmpjx4rp4ok/input0.cc'\nsource_filename = \"/tmp/tmpjx4rp4ok/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index f92e5264e..3e299c64b 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 6cdb2b196..3a689d19b 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/b0b9bd976/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 f2a50c7da..99a8e6622 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/b0b9bd976/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 d7a33aa62..46756fb4f 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/b0b9bd976/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 5f00280e0..fdee75c0e 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/b0b9bd976/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 a44089600..8cea9a9ad 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/b0b9bd976/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 336bed18a..d695cf8d3 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/b0b9bd976/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 1110011dd..7d54dcc07 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/b0b9bd976/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 9d19c6650..3f09c95fe 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/b0b9bd976/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 84e6cf293..26ee01187 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/b0b9bd976/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 e24cedf2e..672fbd8b5 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/b0b9bd976/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 90af3ce09..d3ca1a804 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/b0b9bd976/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 b0dc06b2c..4cd9531d8 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/b0b9bd976/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 4ada5c554..b42d4d8e4 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/b0b9bd976/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 bee8cf2a3..ab04c99dd 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/b0b9bd976/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 afcaff316..752d79cc5 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/b0b9bd976/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 6361c6aa8..cfae935f2 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/b0b9bd976/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 582471550..cd497c722 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/b0b9bd976/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 31ca7579e..7d43e54d2 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/b0b9bd976/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 6db3ef0ee..212bf0530 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/b0b9bd976/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 36698ec74..10e3c402c 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/b0b9bd976/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 ee314e61c..090762345 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/b0b9bd976/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 c6e948c2e..3be8660f0 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/b0b9bd976/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 0a78361ac..e2dec6215 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/b0b9bd976/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 248541de3..5dfae9511 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/b0b9bd976/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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/b0b9bd976/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c9a350c80/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 5c5d1c3f6..a749b5fcd 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 d56f9ebd0..63bbca221 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:22.269</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.389</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:22.262</p></td>
+<td><p>00:21.383</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 1a5a3e362..89e9d75bc 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 24.04s!
+resnet18_v1 inference graph built in 23.25s!
</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 09ba2a76e..66c70ba57 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:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.54s!
+yolov3-tiny inference graph built in 16.11s!
</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 421515e33..1d4ead43b 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>01:34.785</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:32.813</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>00:50.432</p></td>
+<td><p>00:49.248</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:44.353</p></td>
+<td><p>00:43.565</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 62d11a1d0..3a03e28a2 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>00:03.293</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.243</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>00:02.887</p></td>
+<td><p>00:02.846</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>00:00.406</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 aa12b87c5..71c13bb56 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>00:00.750</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.733</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>00:00.410</p></td>
+<td><p>00:00.401</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>00:00.339</p></td>
+<td><p>00:00.333</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 a671f8195..d44eed6ff 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -480,9 +480,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><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">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E*E
-</pre></div>
-</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -570,7 +567,7 @@ 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: 93.436 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.646 ms
</pre></div>
</div>
</div>
@@ -644,7 +641,6 @@ 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 14.897 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 871742687..cfc438a0a 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: 9.29/9.29 result: MeasureResult(costs=(0.0288849552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.600048303604126, timestamp=1660766322.7015827) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.52/9.29 result: MeasureResult(costs=(0.10672176559999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8620357513427734, timestamp=1660766325.1146002) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.80/11.80 result: MeasureResult(costs=(0.0227568016,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5922126770019531, timestamp=1660766325.6832175) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.64/11.80 result: MeasureResult(costs=(0.163207984,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.725649833679199, timestamp=1660766328.998544) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.64/11.80 result: MeasureResult(costs=(0.07382258359999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3251597881317139, timestamp=1660766330.454356) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.69/11.80 result: MeasureResult(costs=(0.159098199,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6759066581726074, timestamp=1660766333.7150173) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.80 result: MeasureResult(costs=(0.30979541599999993,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.079302549362183, timestamp=1660766338.8374858) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 9.92/11.80 result: MeasureResult(costs=(0.027051918,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5881311893463135, timestamp=1660766339.4348228) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.71/11.80 result: MeasureResult(costs=(0.1566016678,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6089847087860107, timestamp=1660766342.163791) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.68/11.80 result: MeasureResult(costs=(0.10009217740000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7074134349822998, timestamp=1660766343.9287486) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.37/9.37 result: MeasureResult(costs=(0.0286575798,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5934884548187256, timestamp=1660773303.7610288) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.23/9.37 result: MeasureResult(costs=(0.1204693158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.078216075897217, timestamp=1660773305.8544705) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.76/11.76 result: MeasureResult(costs=(0.0228277336,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5667085647583008, timestamp=1660773306.9233484) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.84/11.76 result: MeasureResult(costs=(0.1461202098,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.460383653640747, timestamp=1660773309.9600503) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.67/11.76 result: MeasureResult(costs=(0.0732128722,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3065061569213867, timestamp=1660773311.3973153) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.73/11.76 result: MeasureResult(costs=(0.1549511274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.598661422729492, timestamp=1660773314.567383) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.76 result: MeasureResult(costs=(0.3087661896,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.060447692871094, timestamp=1660773319.6701758) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.48/11.76 result: MeasureResult(costs=(0.0256123034,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5521392822265625, timestamp=1660773320.244423) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.89/11.76 result: MeasureResult(costs=(0.1417037224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3667666912078857, timestamp=1660773322.73113) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.77/11.76 result: MeasureResult(costs=(0.0970126398,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6593945026397705, timestamp=1660773324.4480147) [('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 dececd94e..e13f962a5 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 496.84622677000107, 'median': 496.8420989500032, 'std': 1.0463698614272814}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 497.57861620000085, 'median': 497.59652024999923, 'std': 0.3718688564612551}
</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: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 6.48 s
-[Task 1/25] Current/Best: 6.16/ 17.41 GFLOPS | Progress: (8/20) | 9.44 s
-[Task 1/25] Current/Best: 11.51/ 22.67 GFLOPS | Progress: (12/20) | 11.87 s
-[Task 1/25] Current/Best: 16.73/ 22.67 GFLOPS | Progress: (16/20) | 13.57 s
-[Task 1/25] Current/Best: 11.52/ 23.89 GFLOPS | Progress: (20/20) | 15.34 s Done.
+[Task 1/25] Current/Best: 17.51/ 17.51 GFLOPS | Progress: (4/20) | 6.36 s
+[Task 1/25] Current/Best: 6.16/ 17.51 GFLOPS | Progress: (8/20) | 9.33 s
+[Task 1/25] Current/Best: 11.51/ 22.80 GFLOPS | Progress: (12/20) | 11.76 s
+[Task 1/25] Current/Best: 16.82/ 22.83 GFLOPS | Progress: (16/20) | 13.45 s
+[Task 1/25] Current/Best: 11.60/ 23.91 GFLOPS | Progress: (20/20) | 15.19 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.21/ 12.91 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 2/25] Current/Best: 14.18/ 18.82 GFLOPS | Progress: (8/20) | 5.03 s
-[Task 2/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 6.36 s
-[Task 2/25] Current/Best: 12.95/ 19.28 GFLOPS | Progress: (16/20) | 7.63 s
-[Task 2/25] Current/Best: 19.52/ 19.52 GFLOPS | Progress: (20/20) | 9.26 s Done.
+[Task 2/25] Current/Best: 12.28/ 12.87 GFLOPS | Progress: (4/20) | 3.71 s
+[Task 2/25] Current/Best: 14.17/ 17.58 GFLOPS | Progress: (8/20) | 5.04 s
+[Task 2/25] Current/Best: 21.26/ 21.26 GFLOPS | Progress: (12/20) | 6.37 s
+[Task 2/25] Current/Best: 12.24/ 21.26 GFLOPS | Progress: (16/20) | 7.63 s
+[Task 2/25] Current/Best: 18.84/ 21.26 GFLOPS | Progress: (20/20) | 9.20 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/ 10.57 GFLOPS | Progress: (4/20) | 5.91 s
-[Task 3/25] Current/Best: 15.51/ 16.83 GFLOPS | Progress: (8/20) | 7.84 s
-[Task 3/25] Current/Best: 14.80/ 16.83 GFLOPS | Progress: (12/20) | 9.60 s
-[Task 3/25] Current/Best: 7.19/ 23.74 GFLOPS | Progress: (16/20) | 11.53 s
-[Task 3/25] Current/Best: 12.61/ 23.74 GFLOPS | Progress: (20/20) | 16.06 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.56 GFLOPS | Progress: (4/20) | 5.90 s
+[Task 3/25] Current/Best: 15.55/ 16.86 GFLOPS | Progress: (8/20) | 7.82 s
+[Task 3/25] Current/Best: 14.92/ 16.86 GFLOPS | Progress: (12/20) | 9.55 s
+[Task 3/25] Current/Best: 7.06/ 23.86 GFLOPS | Progress: (16/20) | 11.47 s
+[Task 3/25] Current/Best: 12.59/ 23.86 GFLOPS | Progress: (20/20) | 16.15 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.57/ 20.44 GFLOPS | Progress: (4/20) | 2.46 s
-[Task 4/25] Current/Best: 6.32/ 20.44 GFLOPS | Progress: (8/20) | 6.82 s
-[Task 4/25] Current/Best: 21.91/ 21.91 GFLOPS | Progress: (12/20) | 11.31 s
-[Task 4/25] Current/Best: 15.83/ 21.91 GFLOPS | Progress: (16/20) | 13.59 s
-[Task 4/25] Current/Best: 13.09/ 21.91 GFLOPS | Progress: (20/20) | 15.60 s Done.
+[Task 4/25] Current/Best: 9.50/ 18.16 GFLOPS | Progress: (4/20) | 2.45 s
+[Task 4/25] Current/Best: 6.87/ 18.16 GFLOPS | Progress: (8/20) | 6.85 s
+[Task 4/25] Current/Best: 21.67/ 21.67 GFLOPS | Progress: (12/20) | 11.35 s
+[Task 4/25] Current/Best: 16.75/ 21.67 GFLOPS | Progress: (16/20) | 13.60 s
+[Task 4/25] Current/Best: 13.33/ 21.67 GFLOPS | Progress: (20/20) | 15.58 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.66/ 10.23 GFLOPS | Progress: (4/20) | 2.65 s
-[Task 5/25] Current/Best: 11.68/ 12.97 GFLOPS | Progress: (8/20) | 4.71 s
-[Task 5/25] Current/Best: 10.64/ 17.93 GFLOPS | Progress: (12/20) | 7.85 s
-[Task 5/25] Current/Best: 11.71/ 22.62 GFLOPS | Progress: (16/20) | 9.29 s
-[Task 5/25] Current/Best: 11.90/ 22.62 GFLOPS | Progress: (20/20) | 11.17 s Done.
+[Task 5/25] Current/Best: 9.28/ 10.15 GFLOPS | Progress: (4/20) | 2.61 s
+[Task 5/25] Current/Best: 11.57/ 12.59 GFLOPS | Progress: (8/20) | 4.71 s
+[Task 5/25] Current/Best: 11.58/ 18.11 GFLOPS | Progress: (12/20) | 7.84 s
+[Task 5/25] Current/Best: 11.50/ 22.53 GFLOPS | Progress: (16/20) | 9.31 s
+[Task 5/25] Current/Best: 11.99/ 22.53 GFLOPS | Progress: (20/20) | 11.17 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.18/ 20.76 GFLOPS | Progress: (4/20) | 4.06 s
-[Task 6/25] Current/Best: 18.85/ 20.76 GFLOPS | Progress: (8/20) | 5.83 s
-[Task 6/25] Current/Best: 13.29/ 20.76 GFLOPS | Progress: (12/20) | 7.76 s
-[Task 6/25] Current/Best: 19.82/ 20.76 GFLOPS | Progress: (16/20) | 10.06 s
-[Task 6/25] Current/Best: 3.75/ 20.76 GFLOPS | Progress: (20/20) | 12.57 s Done.
+[Task 6/25] Current/Best: 12.26/ 20.70 GFLOPS | Progress: (4/20) | 4.02 s
+[Task 6/25] Current/Best: 18.91/ 20.70 GFLOPS | Progress: (8/20) | 5.79 s
+[Task 6/25] Current/Best: 13.31/ 20.70 GFLOPS | Progress: (12/20) | 7.73 s
+[Task 6/25] Current/Best: 19.70/ 20.70 GFLOPS | Progress: (16/20) | 10.00 s
+[Task 6/25] Current/Best: 3.72/ 20.70 GFLOPS | Progress: (20/20) | 12.52 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.09/ 12.85 GFLOPS | Progress: (4/20) | 3.68 s
-[Task 7/25] Current/Best: 20.18/ 21.13 GFLOPS | Progress: (8/20) | 5.21 s
-[Task 7/25] Current/Best: 15.91/ 21.13 GFLOPS | Progress: (12/20) | 7.17 s
-[Task 7/25] Current/Best: 12.23/ 21.13 GFLOPS | Progress: (16/20) | 9.22 s
-[Task 7/25] Current/Best: 6.38/ 21.72 GFLOPS | Progress: (20/20) | 11.69 s Done.
+[Task 7/25] Current/Best: 11.22/ 12.90 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 7/25] Current/Best: 20.20/ 20.75 GFLOPS | Progress: (8/20) | 5.16 s
+[Task 7/25] Current/Best: 16.03/ 20.75 GFLOPS | Progress: (12/20) | 7.07 s
+[Task 7/25] Current/Best: 12.24/ 20.81 GFLOPS | Progress: (16/20) | 9.12 s
+[Task 7/25] Current/Best: 6.30/ 21.72 GFLOPS | Progress: (20/20) | 11.58 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.89/ 14.40 GFLOPS | Progress: (4/20) | 3.03 s
-[Task 8/25] Current/Best: 9.53/ 14.40 GFLOPS | Progress: (8/20) | 7.80 s
-[Task 8/25] Current/Best: 12.85/ 14.40 GFLOPS | Progress: (12/20) | 13.99 s
-[Task 8/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (16/20) | 16.11 s
-[Task 8/25] Current/Best: 20.00/ 20.00 GFLOPS | Progress: (20/20) | 22.70 s Done.
+[Task 8/25] Current/Best: 9.64/ 14.54 GFLOPS | Progress: (4/20) | 2.97 s
+[Task 8/25] Current/Best: 9.56/ 14.54 GFLOPS | Progress: (8/20) | 7.70 s
+[Task 8/25] Current/Best: 12.60/ 14.54 GFLOPS | Progress: (12/20) | 13.93 s
+[Task 8/25] Current/Best: 18.73/ 18.73 GFLOPS | Progress: (16/20) | 16.05 s
+[Task 8/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (20/20) | 22.57 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.26/ 15.80 GFLOPS | Progress: (4/20) | 11.98 s
-[Task 9/25] Current/Best: 23.45/ 23.45 GFLOPS | Progress: (8/20) | 13.77 s
-[Task 9/25] Current/Best: 8.20/ 23.45 GFLOPS | Progress: (12/20) | 16.14 s
-[Task 9/25] Current/Best: 17.79/ 23.45 GFLOPS | Progress: (16/20) | 18.84 s
-[Task 9/25] Current/Best: 9.12/ 23.45 GFLOPS | Progress: (20/20) | 26.50 s
+[Task 9/25] Current/Best: 14.38/ 15.79 GFLOPS | Progress: (4/20) | 12.00 s
+[Task 9/25] Current/Best: 23.39/ 23.39 GFLOPS | Progress: (8/20) | 13.81 s
+[Task 9/25] Current/Best: 8.24/ 23.39 GFLOPS | Progress: (12/20) | 16.21 s
+[Task 9/25] Current/Best: 18.01/ 23.39 GFLOPS | Progress: (16/20) | 18.89 s
+[Task 9/25] Current/Best: 9.21/ 23.39 GFLOPS | Progress: (20/20) | 26.48 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/20) | 2.59 s
-[Task 10/25] Current/Best: 15.56/ 18.31 GFLOPS | Progress: (8/20) | 4.18 s
-[Task 10/25] Current/Best: 12.58/ 19.00 GFLOPS | Progress: (12/20) | 5.72 s
-[Task 10/25] Current/Best: 18.60/ 20.21 GFLOPS | Progress: (16/20) | 6.84 s
-[Task 10/25] Current/Best: 9.06/ 20.21 GFLOPS | Progress: (20/20) | 8.38 s Done.
+[Task 10/25] Current/Best: 18.24/ 18.24 GFLOPS | Progress: (4/20) | 2.61 s
+[Task 10/25] Current/Best: 15.55/ 18.24 GFLOPS | Progress: (8/20) | 4.20 s
+[Task 10/25] Current/Best: 11.24/ 18.86 GFLOPS | Progress: (12/20) | 5.74 s
+[Task 10/25] Current/Best: 19.13/ 20.24 GFLOPS | Progress: (16/20) | 6.84 s
+[Task 10/25] Current/Best: 8.88/ 20.24 GFLOPS | Progress: (20/20) | 8.38 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 11.62/ 18.10 GFLOPS | Progress: (4/20) | 3.42 s
-[Task 11/25] Current/Best: 16.86/ 18.10 GFLOPS | Progress: (8/20) | 6.16 s
-[Task 11/25] Current/Best: 18.10/ 18.10 GFLOPS | Progress: (12/20) | 8.25 s
-[Task 11/25] Current/Best: 13.50/ 21.09 GFLOPS | Progress: (16/20) | 11.06 s
-[Task 11/25] Current/Best: 19.40/ 21.53 GFLOPS | Progress: (20/20) | 13.09 s Done.
+[Task 11/25] Current/Best: 12.21/ 18.17 GFLOPS | Progress: (4/20) | 3.32 s
+[Task 11/25] Current/Best: 16.32/ 18.17 GFLOPS | Progress: (8/20) | 6.08 s
+[Task 11/25] Current/Best: 18.00/ 18.17 GFLOPS | Progress: (12/20) | 8.10 s
+[Task 11/25] Current/Best: 13.48/ 21.19 GFLOPS | Progress: (16/20) | 10.89 s
+[Task 11/25] Current/Best: 19.45/ 21.59 GFLOPS | Progress: (20/20) | 12.93 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.78/ 18.14 GFLOPS | Progress: (4/20) | 5.45 s
-[Task 12/25] Current/Best: 5.19/ 18.14 GFLOPS | Progress: (8/20) | 9.15 s
-[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (12/20) | 11.17 s
-[Task 12/25] Current/Best: 15.26/ 18.95 GFLOPS | Progress: (16/20) | 13.98 s
-[Task 12/25] Current/Best: 15.07/ 18.95 GFLOPS | Progress: (20/20) | 15.90 s Done.
+[Task 12/25] Current/Best: 7.82/ 18.10 GFLOPS | Progress: (4/20) | 5.37 s
+[Task 12/25] Current/Best: 5.23/ 18.10 GFLOPS | Progress: (8/20) | 9.09 s
+[Task 12/25] Current/Best: 18.71/ 18.75 GFLOPS | Progress: (12/20) | 11.10 s
+[Task 12/25] Current/Best: 15.28/ 18.75 GFLOPS | Progress: (16/20) | 13.90 s
+[Task 12/25] Current/Best: 15.09/ 18.75 GFLOPS | Progress: (20/20) | 15.84 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.88/ 17.19 GFLOPS | Progress: (4/20) | 3.69 s
-[Task 13/25] Current/Best: 16.01/ 20.79 GFLOPS | Progress: (8/20) | 6.15 s
-[Task 13/25] Current/Best: 19.11/ 21.70 GFLOPS | Progress: (12/20) | 9.10 s
-[Task 13/25] Current/Best: 12.22/ 21.70 GFLOPS | Progress: (16/20) | 12.54 s
-[Task 13/25] Current/Best: 18.50/ 21.70 GFLOPS | Progress: (20/20) | 14.79 s Done.
+[Task 13/25] Current/Best: 8.61/ 17.31 GFLOPS | Progress: (4/20) | 3.71 s
+[Task 13/25] Current/Best: 16.11/ 20.78 GFLOPS | Progress: (8/20) | 6.14 s
+[Task 13/25] Current/Best: 19.54/ 21.39 GFLOPS | Progress: (12/20) | 9.10 s
+[Task 13/25] Current/Best: 12.25/ 21.39 GFLOPS | Progress: (16/20) | 12.48 s
+[Task 13/25] Current/Best: 18.42/ 21.39 GFLOPS | Progress: (20/20) | 14.76 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.61/ 13.61 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 14/25] Current/Best: 6.11/ 13.61 GFLOPS | Progress: (8/20) | 5.48 s
-[Task 14/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (12/20) | 8.06 s
-[Task 14/25] Current/Best: 15.55/ 20.81 GFLOPS | Progress: (16/20) | 9.72 s Done.
+[Task 14/25] Current/Best: 13.56/ 13.56 GFLOPS | Progress: (4/20) | 3.28 s
+[Task 14/25] Current/Best: 6.08/ 13.56 GFLOPS | Progress: (8/20) | 5.49 s
+[Task 14/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (12/20) | 8.06 s
+[Task 14/25] Current/Best: 15.88/ 19.95 GFLOPS | Progress: (16/20) | 9.72 s Done.
-[Task 14/25] Current/Best: 17.24/ 20.81 GFLOPS | Progress: (20/20) | 11.47 s
+[Task 14/25] Current/Best: 17.23/ 19.95 GFLOPS | Progress: (20/20) | 11.49 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.05/ 17.64 GFLOPS | Progress: (4/20) | 2.78 s
-[Task 15/25] Current/Best: 14.19/ 17.97 GFLOPS | Progress: (8/20) | 4.09 s
-[Task 15/25] Current/Best: 10.37/ 22.19 GFLOPS | Progress: (12/20) | 6.27 s
-[Task 15/25] Current/Best: 20.21/ 22.19 GFLOPS | Progress: (16/20) | 9.16 s
-[Task 15/25] Current/Best: 9.69/ 22.19 GFLOPS | Progress: (20/20) | 10.14 s
+[Task 15/25] Current/Best: 16.19/ 17.65 GFLOPS | Progress: (4/20) | 2.75 s
+[Task 15/25] Current/Best: 14.44/ 18.07 GFLOPS | Progress: (8/20) | 4.09 s
+[Task 15/25] Current/Best: 10.39/ 22.30 GFLOPS | Progress: (12/20) | 6.16 s
+[Task 15/25] Current/Best: 20.38/ 22.30 GFLOPS | Progress: (16/20) | 9.15 s
+[Task 15/25] Current/Best: 9.53/ 22.30 GFLOPS | Progress: (20/20) | 10.13 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (4/20) | 3.04 s
-[Task 16/25] Current/Best: 3.04/ 19.90 GFLOPS | Progress: (8/20) | 4.66 s
-[Task 16/25] Current/Best: 19.27/ 19.90 GFLOPS | Progress: (12/20) | 5.89 s
-[Task 16/25] Current/Best: 17.85/ 19.90 GFLOPS | Progress: (16/20) | 7.23 s
-[Task 16/25] Current/Best: 9.96/ 22.49 GFLOPS | Progress: (20/20) | 9.28 s Done.
+[Task 16/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (4/20) | 2.99 s
+[Task 16/25] Current/Best: 3.04/ 20.63 GFLOPS | Progress: (8/20) | 4.60 s
+[Task 16/25] Current/Best: 19.56/ 20.63 GFLOPS | Progress: (12/20) | 5.83 s
+[Task 16/25] Current/Best: 17.37/ 20.63 GFLOPS | Progress: (16/20) | 7.20 s
+[Task 16/25] Current/Best: 10.02/ 21.51 GFLOPS | Progress: (20/20) | 9.25 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.98/ 18.82 GFLOPS | Progress: (4/20) | 4.77 s
-[Task 17/25] Current/Best: 14.48/ 22.95 GFLOPS | Progress: (8/20) | 7.65 s
-[Task 17/25] Current/Best: 17.82/ 22.95 GFLOPS | Progress: (12/20) | 9.73 s
-[Task 17/25] Current/Best: 16.49/ 22.95 GFLOPS | Progress: (16/20) | 11.86 s
-[Task 17/25] Current/Best: 10.03/ 22.95 GFLOPS | Progress: (20/20) | 14.00 s Done.
+[Task 17/25] Current/Best: 13.34/ 18.77 GFLOPS | Progress: (4/20) | 4.72 s
+[Task 17/25] Current/Best: 13.99/ 23.02 GFLOPS | Progress: (8/20) | 7.60 s
+[Task 17/25] Current/Best: 17.20/ 23.02 GFLOPS | Progress: (12/20) | 9.65 s
+[Task 17/25] Current/Best: 16.57/ 23.02 GFLOPS | Progress: (16/20) | 11.79 s
+[Task 17/25] Current/Best: 10.04/ 23.02 GFLOPS | Progress: (20/20) | 13.92 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.20/ 18.00 GFLOPS | Progress: (4/20) | 3.75 s
-[Task 18/25] Current/Best: 10.60/ 18.99 GFLOPS | Progress: (8/20) | 7.18 s
-[Task 18/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (12/20) | 9.12 s
-[Task 18/25] Current/Best: 10.11/ 19.12 GFLOPS | Progress: (16/20) | 12.68 s
-[Task 18/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (20/20) | 14.21 s Done.
+[Task 18/25] Current/Best: 11.19/ 17.69 GFLOPS | Progress: (4/20) | 3.73 s
+[Task 18/25] Current/Best: 10.58/ 19.99 GFLOPS | Progress: (8/20) | 7.25 s
+[Task 18/25] Current/Best: 19.31/ 19.99 GFLOPS | Progress: (12/20) | 9.18 s
+[Task 18/25] Current/Best: 10.14/ 19.99 GFLOPS | Progress: (16/20) | 12.79 s
+[Task 18/25] Current/Best: 20.45/ 20.45 GFLOPS | Progress: (20/20) | 14.30 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.14/ 20.28 GFLOPS | Progress: (4/20) | 6.12 s
-[Task 19/25] Current/Best: 2.60/ 20.28 GFLOPS | Progress: (8/20) | 9.39 s
-[Task 19/25] Current/Best: 18.76/ 21.34 GFLOPS | Progress: (12/20) | 12.16 s
-[Task 19/25] Current/Best: 15.08/ 21.34 GFLOPS | Progress: (16/20) | 15.01 s
-[Task 19/25] Current/Best: 2.70/ 23.17 GFLOPS | Progress: (20/20) | 17.79 s Done.
+[Task 19/25] Current/Best: 7.20/ 20.41 GFLOPS | Progress: (4/20) | 6.12 s
+[Task 19/25] Current/Best: 2.60/ 20.41 GFLOPS | Progress: (8/20) | 9.40 s
+[Task 19/25] Current/Best: 20.40/ 21.56 GFLOPS | Progress: (12/20) | 12.29 s
+[Task 19/25] Current/Best: 14.86/ 21.67 GFLOPS | Progress: (16/20) | 15.09 s
+[Task 19/25] Current/Best: 2.69/ 23.39 GFLOPS | Progress: (20/20) | 17.94 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.31/ 14.86 GFLOPS | Progress: (4/20) | 3.37 s Done.
+[Task 20/25] Current/Best: 9.43/ 15.16 GFLOPS | Progress: (4/20) | 3.34 s Done.
Done.
-[Task 20/25] Current/Best: 10.04/ 14.86 GFLOPS | Progress: (8/20) | 6.87 s
-[Task 20/25] Current/Best: 2.32/ 16.60 GFLOPS | Progress: (12/20) | 10.84 s
-[Task 20/25] Current/Best: 12.41/ 16.60 GFLOPS | Progress: (16/20) | 14.63 s
-[Task 20/25] Current/Best: 13.00/ 21.85 GFLOPS | Progress: (20/20) | 16.73 s
+[Task 20/25] Current/Best: 10.14/ 15.16 GFLOPS | Progress: (8/20) | 6.81 s
+[Task 20/25] Current/Best: 2.33/ 16.76 GFLOPS | Progress: (12/20) | 10.74 s
+[Task 20/25] Current/Best: 12.27/ 16.76 GFLOPS | Progress: (16/20) | 14.35 s
+[Task 20/25] Current/Best: 13.22/ 22.04 GFLOPS | Progress: (20/20) | 16.44 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.39/ 17.68 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 21/25] Current/Best: 14.45/ 17.68 GFLOPS | Progress: (8/20) | 4.86 s
-[Task 21/25] Current/Best: 1.61/ 17.68 GFLOPS | Progress: (12/20) | 7.03 s
-[Task 21/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (16/20) | 10.56 s
-[Task 21/25] Current/Best: 4.45/ 17.93 GFLOPS | Progress: (20/20) | 17.86 s
+[Task 21/25] Current/Best: 6.40/ 17.50 GFLOPS | Progress: (4/20) | 3.25 s
+[Task 21/25] Current/Best: 14.62/ 17.50 GFLOPS | Progress: (8/20) | 4.83 s
+[Task 21/25] Current/Best: 1.61/ 17.50 GFLOPS | Progress: (12/20) | 7.02 s
+[Task 21/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (16/20) | 10.49 s
+[Task 21/25] Current/Best: 4.47/ 17.93 GFLOPS | Progress: (20/20) | 17.62 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.80 GFLOPS | Progress: (4/20) | 2.77 s
-[Task 22/25] Current/Best: 9.16/ 21.15 GFLOPS | Progress: (8/20) | 4.77 s
-[Task 22/25] Current/Best: 19.67/ 21.15 GFLOPS | Progress: (12/20) | 7.13 s
-[Task 22/25] Current/Best: 14.96/ 21.15 GFLOPS | Progress: (16/20) | 9.19 s
-[Task 22/25] Current/Best: 14.34/ 21.15 GFLOPS | Progress: (20/20) | 10.88 s Done.
+[Task 22/25] Current/Best: 2.70/ 16.99 GFLOPS | Progress: (4/20) | 2.71 s
+[Task 22/25] Current/Best: 9.18/ 21.60 GFLOPS | Progress: (8/20) | 4.68 s
+[Task 22/25] Current/Best: 19.89/ 21.60 GFLOPS | Progress: (12/20) | 7.00 s
+[Task 22/25] Current/Best: 14.95/ 21.60 GFLOPS | Progress: (16/20) | 9.06 s
+[Task 22/25] Current/Best: 14.64/ 21.60 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: 17.30/ 20.27 GFLOPS | Progress: (4/20) | 3.29 s
-[Task 23/25] Current/Best: 15.84/ 20.27 GFLOPS | Progress: (8/20) | 6.67 s
-[Task 23/25] Current/Best: 20.89/ 21.42 GFLOPS | Progress: (12/20) | 8.52 s
-[Task 23/25] Current/Best: 6.37/ 21.42 GFLOPS | Progress: (16/20) | 15.65 s
-[Task 23/25] Current/Best: 7.78/ 21.42 GFLOPS | Progress: (20/20) | 19.90 s Done.
+[Task 23/25] Current/Best: 17.46/ 20.73 GFLOPS | Progress: (4/20) | 3.29 s
+[Task 23/25] Current/Best: 15.40/ 20.73 GFLOPS | Progress: (8/20) | 6.68 s
+[Task 23/25] Current/Best: 21.03/ 21.65 GFLOPS | Progress: (12/20) | 8.49 s
+[Task 23/25] Current/Best: 6.43/ 21.65 GFLOPS | Progress: (16/20) | 15.58 s
+[Task 23/25] Current/Best: 7.93/ 21.65 GFLOPS | Progress: (20/20) | 19.82 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.44/ 8.44 GFLOPS | Progress: (4/20) | 11.86 s
-[Task 24/25] Current/Best: 3.39/ 8.44 GFLOPS | Progress: (8/20) | 23.14 s
-[Task 24/25] Current/Best: 4.56/ 8.44 GFLOPS | Progress: (12/20) | 33.88 s Done.
+[Task 24/25] Current/Best: 8.00/ 8.00 GFLOPS | Progress: (4/20) | 11.82 s
+[Task 24/25] Current/Best: 2.11/ 8.00 GFLOPS | Progress: (8/20) | 22.85 s
+[Task 24/25] Current/Best: 4.45/ 8.00 GFLOPS | Progress: (12/20) | 34.40 s Done.
-[Task 24/25] Current/Best: 6.19/ 8.57 GFLOPS | Progress: (16/20) | 39.33 s
-[Task 24/25] Current/Best: 3.36/ 8.87 GFLOPS | Progress: (20/20) | 45.33 s Done.
+[Task 24/25] Current/Best: 6.66/ 8.71 GFLOPS | Progress: (16/20) | 39.82 s
+[Task 24/25] Current/Best: 3.27/ 8.96 GFLOPS | Progress: (20/20) | 45.94 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) | 11.63 s
-[Task 25/25] Current/Best: 5.65/ 7.73 GFLOPS | Progress: (8/20) | 22.92 s
-[Task 25/25] Current/Best: 5.66/ 7.73 GFLOPS | Progress: (12/20) | 34.26 s
-[Task 25/25] Current/Best: 5.66/ 9.05 GFLOPS | Progress: (16/20) | 36.04 s
-[Task 25/25] Current/Best: 2.93/ 9.05 GFLOPS | Progress: (20/20) | 46.71 s
+[Task 25/25] Current/Best: 1.55/ 2.76 GFLOPS | Progress: (4/20) | 11.63 s
+[Task 25/25] Current/Best: 5.86/ 7.93 GFLOPS | Progress: (8/20) | 22.92 s
+[Task 25/25] Current/Best: 5.67/ 7.93 GFLOPS | Progress: (12/20) | 34.44 s
+[Task 25/25] Current/Best: 5.85/ 8.41 GFLOPS | Progress: (16/20) | 36.29 s
+[Task 25/25] Current/Best: 2.81/ 8.73 GFLOPS | Progress: (20/20) | 47.01 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -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': 413.2521597000027, 'median': 413.27946029999794, 'std': 0.9055579209214949}
-unoptimized: {'mean': 496.84622677000107, 'median': 496.8420989500032, 'std': 1.0463698614272814}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 408.7253329400005, 'median': 408.8333002500008, 'std': 0.6349661879927168}
+unoptimized: {'mean': 497.57861620000085, 'median': 497.59652024999923, 'std': 0.3718688564612551}
</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 24.053 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 18.784 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 fd58c46a4..c30630b2e 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>1.272e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.266e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 31438606a..125d2ed3a 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, 0x23a9e830)), stage(b, placeholder(b, 0x218e12a0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x1ae3b3d0)), stage(b, placeholder(b, 0x214da950)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 00c532eeb..b25ddc515 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>13:37.529</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:04.866</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>10:24.053</p></td>
+<td><p>10:18.784</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>01:14.897</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>01:02.500</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>01:00.583</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>00:46.471</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>00:31.085</p></td>
+<td><p>00:30.984</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:24.812</p></td>
+<td><p>00:24.236</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.229</p></td>
+<td><p>00:01.035</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.706</p></td>
+<td><p>00:00.704</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>00:00.157</p></td>
+<td><p>00:00.144</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>
@@ -372,10 +372,10 @@
<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>00:00.002</p></td>
+<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
@@ -383,7 +383,7 @@
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index c6c12a56f..8ef23fb65 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -542,8 +542,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
-naive: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+naive: 0.000006
</pre></div>
</div>
</div>
@@ -594,7 +594,7 @@ compile and run this new schedule with the parallel operation applied:</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. "
-parallel: 0.000008
+parallel: 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 6.816699999490083e-06 1.0
- naive 7.6169e-06 1.1173881791144946
-parallel 8.19e-06 1.2014611176394216
- vector 2.4622499999999997e-05 3.6120850267492863
+ numpy 8.094889999483712e-06 1.0
+ naive 5.8407e-06 0.7215292610983617
+parallel 7.087599999999999e-06 0.875564708161821
+ vector 2.46333e-05 3.043067910937777
</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: 0.019723
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018535
</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: 3.364989
+none: 3.531342
</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: 0.300650
+blocking: 0.298599
</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: 0.337639
+vectorization: 0.336347
@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: 0.117698
+loop permutation: 0.117793
@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: 0.110052
+array packing: 0.110395
@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: 0.110667
+block caching: 0.111298
@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: 0.145049
+parallelization: 0.145169
@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 3.3649892858 1.0
- blocking 0.300649999 0.08934649517866824
- vectorization 0.33763905850000003 0.10033882126306057
-loop permutation 0.117697766 0.03497715921315876
- array packing 0.11005166200000001 0.03270490710458119
- block caching 0.1106668524 0.032887728013579635
- parallelization 0.1450493464 0.043105440784640014
+ none 3.5313423024999997 1.0
+ blocking 0.2985993607 0.08455690078206458
+ vectorization 0.3363466034 0.09524610603788955
+loop permutation 0.1177926255 0.033356331788229415
+ array packing 0.1103945744 0.03126136322775807
+ block caching 0.11129787839999998 0.03151715944421675
+ parallelization 0.1451688418 0.041108685979614125
</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 0.583 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.500 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>