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 2022/03/25 17:31:22 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@14084f4c341aae5633b34d11748d3c590237824e)
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 45b585b deploying docs (apache/tvm@14084f4c341aae5633b34d11748d3c590237824e)
45b585b is described below
commit 45b585b41eea409be0054659ac715b1f5c51fe9e
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Mar 25 17:31:18 2022 +0000
deploying docs (apache/tvm@14084f4c341aae5633b34d11748d3c590237824e)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.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 | 4 +-
.../extend_tvm/low_level_custom_pass.rst.txt | 4 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 24 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 534 ++++++++++++++++-----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 99 ++--
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../schedule_primitives.rst.txt | 16 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 4 +-
.../work_with_schedules/tuple_inputs.rst.txt | 22 +-
.../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 +-
.../vta/tutorials/optimize/convolution_opt.rst.txt | 12 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 59 +--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 57 ++-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 19 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 70 ++-
docs/how_to/deploy_models/deploy_prequantized.html | 14 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
docs/how_to/extend_tvm/low_level_custom_pass.html | 4 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 24 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 534 ++++++++++++++++-----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 99 ++--
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/schedule_primitives.html | 16 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 4 +-
docs/how_to/work_with_schedules/tuple_inputs.html | 22 +-
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/convolution_opt.html | 12 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_relay_x86.html | 173 +++----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 53 +-
121 files changed, 1878 insertions(+), 1081 deletions(-)
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 58a07aa..c5ac6db 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip5c40c6be-1325-4f32-9a67-31ced66af4ff from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe6ad9fc2-ee97-499f-a344-eef7c606f586 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_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 4d71fd1..f8e6f6e 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -182,7 +182,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.190 seconds)
+ **Total running time of the script:** ( 1 minutes 20.102 seconds)
.. _sphx_glr_download_how_to_compile_models_from_paddle.py:
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 4114366..8b2fbaf 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ 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]
25%|##5 | 11.2M/44.7M [00:00<00:00, 118MB/s]
60%|###### | 26.9M/44.7M [00:00<00:00, 145MB/s]
91%|#########1| 40.7M/44.7M [00:00<00:00, 112MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 116MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
7%|6 | 3.12M/44.7M [00:00<00:01, 31.9MB/s]
14%|#3 | 6.16M/44.7M [00:00<00:01, 28.9MB/s]
20%|## | 8.94M/44.7M [00:00<00:01, 26.5MB/s]
27%|##7 | 12.2M/44.7M [00:00<00:01, 27.9MB/s]
34%|###3 | 15.0M/44.7M [00:00<00:01, 28.3MB/s]
40%|###9 | 17.7M/44.7M [00:00<00:01, 26.8MB/s]
45%|####5 | 20.3M/44.7M [00:00<00:01, 18.0MB/s]
50%|##### | 22.5M/44.7M [00:01<00:01, 19.2MB/s]
59%|#####8 | 26.2M/44.7M [00:01<00:00, 23.7MB/s]
64%|######4 | 28.7M/44.7M [00:01<00:00, 22.5MB/s]
74%|#######4 | 33.1M/44.7M [00:01<00:00, 28.0MB/s]
82%|########1 | 36.5M/44.7M [00:01<00:00, 29.9MB/s]
88%|########8 | 39.5M/44.7M [00:01<00:00, 29.2MB/s]
95%|#########5| 42.4M/44.7M [00:01<00:00, 27.0MB/s]
100%|##########| 44.7M/44.7M [00:01<00:00, 25.6MB/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 1b8c92e..339ba81 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -380,7 +380,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.982 seconds)
+ **Total running time of the script:** ( 1 minutes 6.945 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 0d427af..16c5860 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
@@ -5,15 +5,15 @@
Computation times
=================
-**05:44.943** total execution time for **how_to_compile_models** files:
+**05:44.574** total execution time for **how_to_compile_models** files:
-- **01:13.982**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **01:07.190**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **00:57.195**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:41.684**: :ref:`sphx_glr_how_to_compile_models_from_caffe2.py` (``from_caffe2.py``)
-- **00:25.248**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:21.677**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:21.566**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:19.613**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:14.138**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.650**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:20.102**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:06.945**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:54.647**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:41.010**: :ref:`sphx_glr_how_to_compile_models_from_caffe2.py` (``from_caffe2.py``)
+- **00:24.513**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:20.581**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:20.567**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:20.071**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.836**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.304**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
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 e177c48..123061a 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
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3047 16.3103 16.4043 16.1583 0.0662
+ 15.6985 15.6811 15.8491 15.5790 0.0836
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 da9b638..38d7126 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
@@ -108,7 +108,7 @@ 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]
1%|1 | 1.80M/170M [00:00<00:09, 18.8MB/s]
2%|2 | 3.62M/170M [00:00<00:09, 18.6MB/s]
9%|9 | 15.4M/170M [00:00<00:02, 66.1MB/s]
20%|#9 | 33.6M/170M [00:00<00:01, 115MB/s]
31%|### | 51.8M/170M [00:00<00:00, 142MB/s]
39%|###9 | 67.1M/170M [00:00<00:00, 147MB/s]
49%|####9 | 83.4M/170M [00:00<00:00, 155MB/s]
58%|#####7 | 98.2M/170M [00:00<00:00, 152MB/s]
66%|######6 | 113M/170M [00:00<00:00, 148MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 151MB/s]
84%|########3 | 142M/170M [00:01<00:00, 151MB/s]
93%|#########2| 157M/170M [00:01<00:00, 154MB/s]
100%|##########| 170M/170M [00:01<00:00, 136MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.68M/170M [00:00<00:03, 49.1MB/s]
6%|5 | 9.36M/170M [00:00<00:04, 38.7MB/s]
8%|7 | 13.3M/170M [00:00<00:04, 39.6MB/s]
11%|# | 18.3M/170M [00:00<00:03, 44.5MB/s]
13%|#3 | 22.7M/170M [00:00<00:03, 41.4MB/s]
16%|#5 | 26.9M/170M [00:00<00:03, 42.2MB/s]
18%|#8 | 31.0M/170M [00:00<00:04, 33.4MB/s]
20%|## | 34.4M/170M [00:01<00:05, 28.3MB/s]
22%|##2 | 37.4M/170M [00:01<00:05, 25.0MB/s]
24%|##3 | 40.0M/170M [00:01<00:05, 22.9MB/s]
25%|##4 | 42.3M/170M [00:01<00:06, 20.4MB/s]
26%|##6 | 44.4M/170M [00:01<00:08, 16.4MB/s]
27%|##7 | 46.6M/170M [00:01<00:07, 17.7MB/s]
29%|##8 | 48.5M/170M [00:02<00:07, 16.0MB/s]
31%|###1 | 53.2M/170M [00:02<00:05, 23.2MB/s]
33%|###3 | 56.9M/170M [00:02<00:04, 26.8MB/s]
35%|###5 | 59.8M/170M [00:02<00:04, 26.8MB/
s]
37%|###7 | 63.1M/170M [00:02<00:03, 29.0MB/s]
39%|###8 | 66.1M/170M [00:02<00:03, 29.2MB/s]
41%|#### | 69.2M/170M [00:02<00:03, 30.1MB/s]
42%|####2 | 72.1M/170M [00:02<00:04, 21.8MB/s]
44%|####3 | 74.7M/170M [00:02<00:04, 22.8MB/s]
45%|####5 | 77.2M/170M [00:03<00:04, 22.1MB/s]
47%|####7 | 80.1M/170M [00:03<00:03, 23.6MB/s]
49%|####8 | 82.5M/170M [00:03<00:04, 21.6MB/s]
50%|##### | 85.8M/170M [00:03<00:03, 24.5MB/s]
52%|#####1 | 88.2M/170M [00:03<00:03, 22.2MB/s]
54%|#####3 | 91.1M/170M [00:03<00:03, 24.1MB/s]
55%|#####5 | 93.9M/170M [00:03<00:03, 25.0MB/s]
57%|#####7 | 97.0M/170M [00:03<00:02, 27.1MB/s]
59%|#####8 | 99.7M/170M [00:04<00:02, 25.5MB/s]
60%|###### | 102M/170M [00:04<00:02, 25.6MB/s]
62%|######1 | 105M/170M [00:04<00:02, 25.9MB/s]
63%|######3 | 107M/170M [00:04<00:02, 23.5MB/s]
65%|######4 | 110M/170M [00:04<00:02,
23.5MB/s]
67%|######6 | 113M/170M [00:04<00:02, 26.7MB/s]
69%|######8 | 117M/170M [00:04<00:01, 30.9MB/s]
71%|####### | 120M/170M [00:04<00:01, 27.7MB/s]
72%|#######2 | 123M/170M [00:05<00:02, 21.5MB/s]
74%|#######3 | 125M/170M [00:05<00:02, 18.8MB/s]
75%|#######5 | 127M/170M [00:05<00:02, 19.0MB/s]
76%|#######6 | 129M/170M [00:05<00:02, 19.0MB/s]
78%|#######8 | 133M/170M [00:05<00:01, 22.1MB/s]
80%|######## | 136M/170M [00:05<00:01, 25.0MB/s]
82%|########1 | 138M/170M [00:05<00:01, 24.7MB/s]
83%|########2 | 141M/170M [00:05<00:01, 24.4MB/s]
85%|########4 | 144M/170M [00:05<00:01, 25.0MB/s]
86%|########5 | 146M/170M [00:06<00:01, 22.5MB/s]
88%|########8 | 150M/170M [00:06<00:00, 28.0MB/s]
90%|######### | 153M/170M [00:06<00:00, 29.8MB/s]
92%|#########2| 156M/170M [00:06<00:00, 30.2MB/s]
94%|#########4| 160M/170M [00:06<00:00, 33.3MB/s]
96%|#########6| 164M/170M [00:06<00:00, 28.5MB
/s]
99%|#########8| 168M/170M [00:06<00:00, 32.7MB/s]
100%|##########| 170M/170M [00:06<00:00, 26.1MB/s]
/usr/local/lib/python3.7/dist-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3702: 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).
@@ -255,7 +255,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 11.492 seconds)
+ **Total running time of the script:** ( 3 minutes 5.785 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 096156f..a3f5a39 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ 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]
30%|##9 | 4.06M/13.6M [00:00<00:00, 39.3MB/s]
81%|######## | 11.0M/13.6M [00:00<00:00, 57.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 56.1MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
5%|5 | 728k/13.6M [00:00<00:01, 7.13MB/s]
10%|# | 1.40M/13.6M [00:00<00:01, 6.71MB/s]
32%|###1 | 4.32M/13.6M [00:00<00:00, 15.1MB/s]
49%|####9 | 6.68M/13.6M [00:00<00:00, 16.8MB/s]
61%|###### | 8.23M/13.6M [00:00<00:00, 13.8MB/s]
99%|#########8| 13.4M/13.6M [00:00<00:00, 24.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 18.9MB/s]
@@ -348,7 +348,7 @@ 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)
- 90.2868 90.2253 92.9443 90.0490 0.3068
+ 90.5035 90.1648 109.1200 89.8791 2.0112
@@ -388,7 +388,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.091 seconds)
+ **Total running time of the script:** ( 1 minutes 3.925 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 2701ba1..7d11a6f 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
@@ -351,7 +351,7 @@ 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)
- 120.3628 120.3502 122.3226 119.6968 0.4207
+ 117.9394 117.9172 119.7118 116.7910 0.5408
@@ -385,7 +385,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 54.164 seconds)
+ **Total running time of the script:** ( 1 minutes 52.985 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 95e0a83..6653446 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.133 seconds)
+ **Total running time of the script:** ( 1 minutes 17.828 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 921e886..42c6834 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
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5270/132723 [00:00<00:02, 52692.14KB/s]
10%|# | 13310/132723 [00:00<00:01, 68984.31KB/s]
16%|#6 | 21380/132723 [00:00<00:01, 74329.43KB/s]
22%|##2 | 29424/132723 [00:00<00:01, 76739.12KB/s]
28%|##8 | 37426/132723 [00:00<00:01, 77919.49KB/s]
34%|###4 | 45465/132723 [00:00<00:01, 78754.77KB/s]
40%|#### | 53444/132723 [00:00<00:01, 79091.30KB/s]
46%|####6 | 61478/132723 [00:00<00:00, 79487.43KB/s]
52%|#####2 | 69536/132723 [00:00<00:00, 79826.31KB/s]
58%|#####8 | 77519/132723 [00:01<00:00, 79781.85KB/s]
64%|######4 | 85498/132723 [00:01<00:00, 79725.87KB/s]
70%|####### | 93542/132723 [00:01<00:00, 79940.29KB/s]
77%|#######6 | 101537/132723 [00:01<00:00, 79866.70KB/s]
83%|########2 | 109524/132723 [00:01<00:00, 79747.53KB/s]
89%|########8 | 117520/132723 [00:01<00:00, 79808.33KB/s]
95%|########
#4| 125573/132723 [00:01<00:00, 80023.86KB/s]
100%|##########| 132723/132723 [00:01<00:00, 78522.26KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 3983/132723 [00:00<00:03, 39827.95KB/s]
7%|7 | 9755/132723 [00:00<00:02, 50347.76KB/s]
14%|#3 | 18308/132723 [00:00<00:01, 66402.34KB/s]
20%|## | 26941/132723 [00:00<00:01, 74264.35KB/s]
27%|##6 | 35534/132723 [00:00<00:01, 78469.26KB/s]
33%|###3 | 44164/132723 [00:00<00:01, 81122.70KB/s]
40%|###9 | 52596/132723 [00:00<00:00, 82166.71KB/s]
46%|####6 | 61270/132723 [00:00<00:00, 83619.40KB/s]
53%|#####2 | 69956/132723 [00:00<00:00, 84629.99KB/s]
59%|#####9 | 78645/132723 [00:01<00:00, 85326.23KB/s]
66%|######5 | 87309/132723 [00:01<00:00, 85726.18KB/s]
72%|#######2 | 95913/132723 [00:01<00:00, 85820.36KB/s]
79%|#######8 | 104542/132723 [00:01<00:00, 85956.19KB/s]
85%|########5 | 113270/132723 [00:01<00:00, 86354.67KB/s]
92%|#########1| 121906/132723 [00:01<00:00, 86275.95KB/s]
98%|#########
8| 130534/132723 [00:01<00:00, 86060.87KB/s]
100%|##########| 132723/132723 [00:01<00:00, 81502.77KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 28.546 seconds)
+ **Total running time of the script:** ( 2 minutes 18.803 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 eba5e05..46bfee8 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
@@ -5,13 +5,13 @@
Computation times
=================
-**10:53.712** total execution time for **how_to_deploy_models** files:
+**10:27.992** total execution time for **how_to_deploy_models** files:
-- **03:11.492**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:28.546**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:54.164**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:21.133**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:07.091**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:29.133**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:21.937**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.216**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:05.785**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:18.803**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:52.985**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:17.828**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:03.925**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.271**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.201**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.195**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
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 9ede8bb..1e67620 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
@@ -423,7 +423,7 @@ 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.zipe4018526-8958-4625-b745-14a855bac435 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip19c3c456-218b-4d24-a9cf-8979116f4484 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -525,7 +525,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
.. code-block:: none
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
diff --git a/docs/_sources/how_to/extend_tvm/low_level_custom_pass.rst.txt b/docs/_sources/how_to/extend_tvm/low_level_custom_pass.rst.txt
index 784da15..e4a71e8 100644
--- a/docs/_sources/how_to/extend_tvm/low_level_custom_pass.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/low_level_custom_pass.rst.txt
@@ -73,8 +73,8 @@ our customized lowering pass to manipulate the IR directly instead of using sche
@main = primfn(a_1: handle, b_1: handle, c_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {c: Buffer(c_2: Pointer(float32), float32, [128], []),
- a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ buffers = {a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ c: Buffer(c_2: Pointer(float32), float32, [128], []),
b: Buffer(b_2: Pointer(float32), float32, [128], [])}
buffer_map = {a_1: a, b_1: b, c_1: c} {
for (i: int32, 0, 128) {
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 dad7776..a54e4d2 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
@@ -5,9 +5,9 @@
Computation times
=================
-**00:39.612** total execution time for **how_to_extend_tvm** files:
+**00:37.594** total execution time for **how_to_extend_tvm** files:
-- **00:35.902**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.359**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.130**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.221**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.093**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.239**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.065**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.197**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
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 e6c023a..c6fb835 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
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6382us [6382us] (45.72%; 45.72%)
- FoldScaleAxis: 7578us [2us] (54.28%; 54.28%)
- FoldConstant: 7576us [1573us] (54.27%; 99.97%)
- InferType: 6003us [6003us] (43.00%; 79.24%)
+ InferType: 6014us [6014us] (44.76%; 44.76%)
+ FoldScaleAxis: 7422us [2us] (55.24%; 55.24%)
+ FoldConstant: 7420us [1499us] (55.23%; 99.97%)
+ InferType: 5922us [5922us] (44.07%; 79.80%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6268us [6268us] (45.31%; 45.31%)
- FoldScaleAxis: 7565us [2us] (54.69%; 54.69%)
- FoldConstant: 7563us [1589us] (54.67%; 99.97%)
- InferType: 5973us [5973us] (43.18%; 78.98%)
+ InferType: 6139us [6139us] (44.82%; 44.82%)
+ FoldScaleAxis: 7557us [2us] (55.18%; 55.18%)
+ FoldConstant: 7555us [1655us] (55.16%; 99.97%)
+ InferType: 5900us [5900us] (43.08%; 78.09%)
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 9b9efc9..5e28dcf 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
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 43.128546 ms
+ Convolution: 54.139155 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 705da93..e16e17c 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
@@ -626,7 +626,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.665528 ms
+ conv2d with tensor core: 6.634120 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 1c47978..9b2e373 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019299
- Baseline: 3.253213
+ Numpy running time: 0.017750
+ Baseline: 3.443008
@@ -209,7 +209,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.314582
+ Opt1: 0.303428
@@ -233,8 +233,8 @@ Here is the generated IR after blocking.
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (m.outer: int32, 0, 32) {
@@ -307,7 +307,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.346832
+ Opt2: 0.332963
@@ -331,8 +331,8 @@ Here is the generated IR after vectorization.
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (m.outer: int32, 0, 32) {
@@ -398,7 +398,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.119707
+ Opt3: 0.114610
@@ -516,7 +516,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111440
+ Opt4: 0.110934
@@ -633,7 +633,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111517
+ Opt5: 0.111276
@@ -753,7 +753,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.146105
+ Opt6: 0.144939
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 24c11b8..94911a7 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:35.226** total execution time for **how_to_optimize_operators** files:
+**00:35.055** total execution time for **how_to_optimize_operators** files:
-- **00:32.461**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.524**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.241**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.398**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.412**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.245**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
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 8eb3ed2..1aabb77 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
@@ -5,11 +5,11 @@
Computation times
=================
-**05:12.234** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:25.299**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:21.536**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:41.142**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:26.725**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.863**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.669**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**04:49.359** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:16.909**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:19.027**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.003**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:16.964**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.273**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.183**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
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 d4fce68..535ad05 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
@@ -221,63 +221,226 @@ cooperative fetching, unrolling and operator fusion.
data: Buffer(data_2: Pointer(float32), float32, [25088], []),
kernel: Buffer(kernel_2: Pointer(float32), float32, [2359296], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 224;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [84]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [192]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ 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" = 112 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[1] = 0f32
for (rc.outer.outer: int32, 0, 128) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*36)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [84], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer) < 8)) && (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, 3)*7)) + (ry.outer.outer*7)) + floo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 28), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[((((((rc.outer.outer*196) + (floordiv((threadIdx.x_1 + 56), 3)*7)) + (ry.outer.outer*7)) + floormod(blockIdx.x, 7 [...]
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [192], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 12), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 12), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 12), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((((floordiv(blockIdx.x, 7)*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 12), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
- 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)*24) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
- 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)*24) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 43)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 43)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 44)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 44)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ let cse_var_1: int32 = (rc.outer.outer*36)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[(threadIdx.x_1*36)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 1)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 2)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 3)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 5)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 4)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 4)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 5)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 3)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 6)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 2)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 7)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 1)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 8)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 9)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 10)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 11)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 12)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 5)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 13)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 4)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 14)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 3)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 15)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 2)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 16)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 1)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 17)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 18)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 19)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 20)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 21)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 5)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 22)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 4)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 23)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 3)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 24)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 2)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 25)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 1)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 26)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 27)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 28)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 42)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 29)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 43)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 30)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 44)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 31)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 45)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 32)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 46)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 33)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 47)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 34)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 48)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 35)] = 0f32
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ 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" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv(floordiv(threadIdx.x_2, 4), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
}
}
for (i1.inner: int32, 0, 2) {
- compute[(((((floordiv(blockIdx.x, 7)*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((floordiv(blockIdx.x, 7)*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((floordiv(blockIdx.x, 7)*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -330,7 +493,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.414 ms
+ Execution time of this operator: 0.439 ms
@@ -376,34 +539,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_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=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=8)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -423,14 +586,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=36)
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=56)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -448,54 +611,211 @@ 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__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[2];
- __shared__ float pad_temp_shared[84];
- __shared__ float kernel_shared[192];
+ __shared__ float pad_temp_shared[108];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 28) {
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3) [...]
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 24) {
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- }
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 43)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 43)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 44)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 44)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ __syncthreads();
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[(((int)threadIdx.x) * 36)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 1)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 2)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 3)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 5)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 4)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 4)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 5)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 3)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 6)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 2)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 7)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 8)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 9)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 10)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 11)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 12)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 5)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 13)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 4)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 14)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 3)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 15)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 2)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 16)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 17)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 18)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 19)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 20)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 21)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 5)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 22)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 4)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 23)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 3)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 24)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 2)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 25)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 26)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 27)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 28)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 42)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 29)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 43)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 30)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 44)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 31)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 45)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 32)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 46)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 33)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 47)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 34)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 48)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 35)] = 0.000000e+00f;
+ }
+ 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) + 112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 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))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 12) % 36))];
+ 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))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 20) % 36))];
+ 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) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ 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))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 129024)];
+ 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))];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -554,7 +874,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 25.299 seconds)
+ **Total running time of the script:** ( 2 minutes 16.909 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 35adc77..496ff60 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
@@ -614,7 +614,7 @@ 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)
- 9.7643 9.7568 9.7889 9.7473 0.0178
+ 9.9811 9.9866 10.0053 9.9513 0.0224
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 d435e5b..cb30e3e 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
@@ -633,7 +633,7 @@ 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)
- 764.3591 761.8650 769.4652 761.7469 3.6109
+ 761.2881 762.2861 764.8818 756.6965 3.4153
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.536 seconds)
+ **Total running time of the script:** ( 1 minutes 19.027 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 2c1d6fc..174f2e7 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
@@ -355,37 +355,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
Lowered TIR:
@main = primfn(placeholder_5: handle, placeholder_6: handle, placeholder_7: handle, placeholder_8: handle, placeholder_9: handle, compute_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {placeholder_4: Buffer(placeholder_10: Pointer(int32), int32, [4916], []),
- placeholder_3: Buffer(placeholder_11: Pointer(float32), float32, [32768], []),
- compute: Buffer(compute_2: Pointer(float32), float32, [65536], []),
- placeholder: Buffer(placeholder_12: Pointer(float32), float32, [65536], []),
- placeholder_2: Buffer(placeholder_13: Pointer(float32), float32, [78656], []),
- placeholder_1: Buffer(placeholder_14: Pointer(int32), int32, [33], [])}
- buffer_map = {placeholder_9: placeholder, placeholder_8: placeholder_1, placeholder_6: placeholder_2, compute_1: compute, placeholder_5: placeholder_3, placeholder_7: placeholder_4} {
- allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [4096], [])[((((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ buffers = {placeholder_3: Buffer(placeholder_10: Pointer(float32), float32, [78656], []),
+ placeholder_4: Buffer(placeholder_11: Pointer(int32), int32, [4916], []),
+ placeholder_2: Buffer(placeholder_12: Pointer(float32), float32, [65536], []),
+ placeholder_1: Buffer(placeholder_13: Pointer(float32), float32, [32768], []),
+ placeholder: Buffer(placeholder_14: Pointer(int32), int32, [33], []),
+ compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
+ buffer_map = {placeholder_8: placeholder, compute_1: compute, placeholder_5: placeholder_1, placeholder_9: placeholder_2, placeholder_6: placeholder_3, placeholder_7: placeholder_4} {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = (i.inner.init*16)
+ {
+ compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_1[(cse_var_1 + 1)] - placeholder_1[cse_var_1])) {
- for (i.inner: int32, 0, 32) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_2[(((placeholder_1[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_3[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_4[(placeholder_1[cse_var_3] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder[(cse_var_2 + 1)] - placeholder[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_20: int32 = (i.inner*16)
+ let cse_var_19: int32 = (elem_idx*16)
+ let cse_var_18: int32 = (cse_var_20 + 10)
+ let cse_var_17: int32 = (cse_var_20 + 11)
+ let cse_var_16: int32 = (cse_var_20 + 12)
+ let cse_var_15: int32 = (cse_var_20 + 13)
+ let cse_var_14: int32 = (cse_var_20 + 14)
+ let cse_var_13: int32 = (cse_var_20 + 15)
+ let cse_var_12: int32 = (cse_var_20 + 2)
+ let cse_var_11: int32 = (cse_var_20 + 3)
+ let cse_var_10: int32 = (cse_var_20 + 4)
+ let cse_var_9: int32 = (cse_var_20 + 5)
+ let cse_var_8: int32 = (cse_var_20 + 6)
+ let cse_var_7: int32 = (cse_var_20 + 7)
+ let cse_var_6: int32 = (cse_var_20 + 8)
+ let cse_var_5: int32 = (cse_var_20 + 9)
+ let cse_var_4: int32 = (cse_var_20 + 1)
+ let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256))
+ {
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_3[((placeholder[cse_var_21]*16) + cse_var_19)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 1)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 2)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 3)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 4)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 5)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 6)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 7)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 8)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 9)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 10)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 11)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 12)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 13)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 14)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 15)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
- }
- for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((i0.inner*512) + (i1.outer*32)) + i1.inner)
- compute[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder[cse_var_4]), 0f32)
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_22, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_2[ramp(cse_var_22, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -439,7 +482,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.488 ms
+ Execution time of this operator: 1.925 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 e35aa56..a5a265a 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:45.031** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.255** total execution time for **how_to_tune_with_autotvm** files:
-- **00:44.084**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.246**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.234**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.234**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.232**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:43.395**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.218**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.210**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
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 379f046..4c444b7 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
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 42.27/42.27 result: MeasureResult(costs=(0.0054765041578947364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6218910217285156, timestamp=1648221606.4856763) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 94.35/94.35 result: MeasureResult(costs=(0.002453696416666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7631030082702637, timestamp=1648223399.4223347) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/94.35 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
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f49d5fcafa2
+ 12: 0x00007f2fbd65dfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 144.64/144.64 result: MeasureResult(costs=(0.0016004863800000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4456572532653809, timestamp=1648221633.0995505) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 143.12/143.12 result: MeasureResult(costs=(0.0016175155555555557,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1329972743988037, timestamp=1648223425.5728607) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.002029
+ Time cost of this operator: 0.002034
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 42079cb..7712ead 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
@@ -292,10 +292,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.2 98.752 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.96 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.288 (1, 1, 10, 10, 3) 1 1
- Total_time - 320.196 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.9 98.658 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.178 0.993 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.12 0.35 (1, 1, 10, 10, 3) 1 1
+ Total_time - 320.198 - - - -
@@ -357,10 +357,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 190.2 98.511 (1, 1, 10, 10, 6) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.948 1.009 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.927 0.48 (1, 3, 10, 10, 1) 1 1
- Total_time - 193.075 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 217.2 98.68 (1, 1, 10, 10, 6) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.961 0.891 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.945 0.429 (1, 3, 10, 10, 1) 1 1
+ Total_time - 220.106 - - - -
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 f1e879a..71f0293 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:46.456** total execution time for **how_to_work_with_microtvm** files:
+**00:44.090** total execution time for **how_to_work_with_microtvm** files:
-- **00:42.101**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.714**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.216**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.215**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.210**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:40.033**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.499**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.188**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.186**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.183**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
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 6aa5546..cde8911 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:04.588** total execution time for **how_to_work_with_relay** files:
+**00:04.548** total execution time for **how_to_work_with_relay** files:
-- **00:02.616**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.735**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.236**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:02.511**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.830**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.208**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/schedule_primitives.rst.txt b/docs/_sources/how_to/work_with_schedules/schedule_primitives.rst.txt
index c920e2c..f6558fe 100644
--- a/docs/_sources/how_to/work_with_schedules/schedule_primitives.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/schedule_primitives.rst.txt
@@ -416,15 +416,15 @@ tensors at the root separately by default.
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- A: Buffer(A_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, m) {
- B[(i*stride_2)] = (A[(i*stride_1)] + 1f32)
+ B[(i*stride_2)] = (A[(i*stride)] + 1f32)
}
for (i_1: int32, 0, m) {
- C[(i_1*stride)] = (B[(i_1*stride_2)]*2f32)
+ C[(i_1*stride_1)] = (B[(i_1*stride_2)]*2f32)
}
}
@@ -458,13 +458,13 @@ of computation of `C`.
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- A: Buffer(A_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, m) {
- B[(i*stride_2)] = (A[(i*stride_1)] + 1f32)
- C[(i*stride)] = (B[(i*stride_2)]*2f32)
+ B[(i*stride_2)] = (A[(i*stride)] + 1f32)
+ C[(i*stride_1)] = (B[(i*stride_2)]*2f32)
}
}
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 7956ece..db710ba 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
@@ -5,13 +5,13 @@
Computation times
=================
-**00:06.329** total execution time for **how_to_work_with_schedules** files:
+**00:06.015** total execution time for **how_to_work_with_schedules** files:
-- **00:02.319**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.313**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.806**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.795**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.346**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.258**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.252**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.241**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.235**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.272**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.755**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.754**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.314**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.242**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.231**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.212**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
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 0e3ab94..a3dfb72 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -314,8 +314,8 @@ The importing needs to happen before the tensorized GEMV being executed.
A: Buffer(A_2: Pointer(float32), float32, [65536], []),
B: Buffer(B_2: Pointer(float32), float32, [32768], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp8bd7_y5r/input0.cc'
- source_filename = "/tmp/tmp8bd7_y5r/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpthaxxy9l/input0.cc'
+ source_filename = "/tmp/tmpthaxxy9l/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
diff --git a/docs/_sources/how_to/work_with_schedules/tuple_inputs.rst.txt b/docs/_sources/how_to/work_with_schedules/tuple_inputs.rst.txt
index d660271..06e9a08 100644
--- a/docs/_sources/how_to/work_with_schedules/tuple_inputs.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tuple_inputs.rst.txt
@@ -135,17 +135,17 @@ with :py:func:`te.comm_reducer` as below:
@main = primfn(idx_1: handle, val_1: handle, T_2: handle, T_3: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {T: Buffer(T_4: Pointer(int32), int32, [(stride: int32*m: int32)], [], type="auto"),
- T_1: Buffer(T_5: Pointer(int32), int32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {T_1: Buffer(T_4: Pointer(int32), int32, [(stride: int32*m: int32)], [], type="auto"),
+ T: Buffer(T_5: Pointer(int32), int32, [(stride_1: int32*m)], [], type="auto"),
idx: Buffer(idx_2: Pointer(int32), int32, [(stride_2: int32*m)], [], type="auto"),
val: Buffer(val_2: Pointer(int32), int32, [(stride_3: int32*m)], [], type="auto")}
buffer_map = {idx_1: idx, val_1: val, T_2: T, T_3: T_1} {
for (i: int32, 0, m) {
- T[(i*stride)] = -1
- T_1[(i*stride_1)] = -2147483648
+ T[(i*stride_1)] = -1
+ T_1[(i*stride)] = -2147483648
for (k: int32, 0, n: int32) {
- T[(i*stride)] = @tir.if_then_else((val[((i*stride_3) + (k*stride_4: int32))] <= T_1[(i*stride_1)]), T[(i*stride)], idx[((i*stride_2) + (k*stride_5: int32))], dtype=int32)
- T_1[(i*stride_1)] = @tir.if_then_else((val[((i*stride_3) + (k*stride_4))] <= T_1[(i*stride_1)]), T_1[(i*stride_1)], val[((i*stride_3) + (k*stride_4))], dtype=int32)
+ T[(i*stride_1)] = @tir.if_then_else((val[((i*stride_3) + (k*stride_4: int32))] <= T_1[(i*stride)]), T[(i*stride_1)], idx[((i*stride_2) + (k*stride_5: int32))], dtype=int32)
+ T_1[(i*stride)] = @tir.if_then_else((val[((i*stride_3) + (k*stride_4))] <= T_1[(i*stride)]), T_1[(i*stride)], val[((i*stride_3) + (k*stride_4))], dtype=int32)
}
}
}
@@ -193,19 +193,19 @@ in terms of operation.
@main = primfn(A0_1: handle, A1_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {A0: Buffer(A0_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ A0: Buffer(A0_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
A1: Buffer(A1_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto")}
buffer_map = {A0_1: A0, A1_1: A1, C_1: C} {
allocate(B.v0: Pointer(global float32), float32, [n: int32]), storage_scope = global;
allocate(B.v1: Pointer(global float32), float32, [n]), storage_scope = global;
for (i: int32, 0, m) {
for (j: int32, 0, n) {
- B.v0_1: Buffer(B.v0, float32, [n], [])[j] = (A0[((i*stride) + (j*stride_3: int32))] + 2f32)
- B.v1_1: Buffer(B.v1, float32, [n], [])[j] = (A0[((i*stride) + (j*stride_3))]*3f32)
+ B.v0_1: Buffer(B.v0, float32, [n], [])[j] = (A0[((i*stride_1) + (j*stride_3: int32))] + 2f32)
+ B.v1_1: Buffer(B.v1, float32, [n], [])[j] = (A0[((i*stride_1) + (j*stride_3))]*3f32)
}
for (j_1: int32, 0, n) {
- C[((i*stride_1) + (j_1*stride_4: int32))] = (A1[((i*stride_2) + (j_1*stride_5: int32))] + B.v0_1[j_1])
+ C[((i*stride) + (j_1*stride_4: int32))] = (A1[((i*stride_2) + (j_1*stride_5: int32))] + B.v0_1[j_1])
}
}
}
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 70ab96e..cf2b32d 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:20.900** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:19.635** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.677**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.223**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:19.435**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.200**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
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 bf082c7..d8e39fa 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.36s!
+ resnet18_v1 inference graph built in 20.49s!
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 f61720f..57b4f78 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.22s!
+ yolov3-tiny inference graph built in 14.22s!
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 b2ac117..5f93c87 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
@@ -5,7 +5,7 @@
Computation times
=================
-**01:29.572** total execution time for **topic_vta_tutorials_frontend** files:
+**01:25.742** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:47.149**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:42.423**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:45.509**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:40.233**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
diff --git a/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
index f11362d..4286aaf 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
@@ -252,8 +252,8 @@ Those include:
@main = primfn(data_1: handle, kernel_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {data: Buffer(data_2: Pointer(int8), int8, [50176], []),
- res: Buffer(res_2: Pointer(int8), int8, [50176], []),
+ buffers = {res: Buffer(res_2: Pointer(int8), int8, [50176], []),
+ data: Buffer(data_2: Pointer(int8), int8, [50176], []),
kernel: Buffer(kernel_2: Pointer(int8), int8, [589824], [])}
buffer_map = {data_1: data, kernel_1: kernel, res_1: res} {
allocate(data_buf: Pointer(global int8), int8, [65536]), storage_scope = global;
@@ -453,8 +453,8 @@ below.
@main = primfn(data_1: handle, kernel_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {res: Buffer(res_2: Pointer(int8), int8, [50176], []),
- data: Buffer(data_2: Pointer(int8), int8, [50176], []),
+ buffers = {data: Buffer(data_2: Pointer(int8), int8, [50176], []),
+ res: Buffer(res_2: Pointer(int8), int8, [50176], []),
kernel: Buffer(kernel_2: Pointer(int8), int8, [589824], [])}
buffer_map = {data_1: data, kernel_1: kernel, res_1: res} {
allocate(data_buf: Pointer(global int8), int8, [65536]), storage_scope = global;
@@ -663,8 +663,8 @@ and mapping the shift, and clipping computation to the vector ALU.
@main = primfn(data_1: handle, kernel_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {data: Buffer(data_2: Pointer(int8), int8, [50176], []),
- res: Buffer(res_2: Pointer(int8), int8, [50176], []),
+ buffers = {res: Buffer(res_2: Pointer(int8), int8, [50176], []),
+ data: Buffer(data_2: Pointer(int8), int8, [50176], []),
kernel: Buffer(kernel_2: Pointer(int8), int8, [589824], [])}
buffer_map = {data_1: data, kernel_1: kernel, res_1: res} {
@tir.vta.coproc_dep_push(3, 2, dtype=int32)
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 4a7495a..206ce49 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.648** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.553** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.039**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.609**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.989**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.564**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
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 7ec89eb..4dfd63b 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:01.107** total execution time for **topic_vta_tutorials** files:
+**00:01.036** total execution time for **topic_vta_tutorials** files:
-- **00:00.554**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
-- **00:00.553**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.524**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.511**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 4b67d33..05e50c5 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -184,7 +184,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
-
+ *E
@@ -217,8 +217,8 @@ operator fusion.
@main = primfn(A_1: handle, B_1: handle, C_1: handle, out_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {out: Buffer(out_2: Pointer(float32), float32, [1048576], []),
- C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C, out_1: out} {
allocate(auto_scheduler_layout_transform: Pointer(global float32), float32, [1048576]), storage_scope = global {
@@ -305,7 +305,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.515 ms
+ Execution time of this operator: 95.852 ms
@@ -414,6 +414,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 14.937 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index b7543e7..9b75b53 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -268,7 +268,7 @@ standard deviation.
.. code-block:: none
- {'mean': 498.4630057199991, 'median': 498.29967405000275, 'std': 0.5841999958077553}
+ {'mean': 491.0830640700011, 'median': 491.01350355000477, 'std': 0.4615301791043869}
@@ -482,30 +482,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 17.83/ 21.13 GFLOPS | Progress: (4/10) | 5.10 s
[Task 1/25] Current/Best: 14.30/ 23.49 GFLOPS | Progress: (8/10) | 8.20 s
[Task 1/25] Current/Best: 12.96/ 23.49 GFLOPS | Progress: (10/10) | 9.05 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 8.73/ 16.70 GFLOPS | Progress: (4/10) | 2.80 s
[Task 2/25] Current/Best: 17.97/ 17.97 GFLOPS | Progress: (8/10) | 4.65 s
[Task 2/25] Current/Best: 14.58/ 17.97 GFLOPS | Progress: (10/10) | 5.22 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 6.27/ 17.55 GFLOPS | Progress: (4/10) | 3.50 s
[Task 3/25] Current/Best: 20.75/ 20.75 GFLOPS | Progress: (8/10) | 5.32 s
[Task 3/25] Current/Best: 13.53/ 20.75 GFLOPS | Progress: (10/10) | 6.87 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 6.63/ 16.08 GFLOPS | Progress: (4/10) | 2.77 s
[Task 4/25] Current/Best: 13.61/ 16.08 GFLOPS | Progress: (8/10) | 6.94 s
[Task 4/25] Current/Best: 12.49/ 16.08 GFLOPS | Progress: (10/10) | 7.93 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 5.68/ 22.60 GFLOPS | Progress: (4/10) | 2.56 s
[Task 5/25] Current/Best: 22.45/ 22.60 GFLOPS | Progress: (8/10) | 4.10 s
[Task 5/25] Current/Best: 18.58/ 22.60 GFLOPS | Progress: (10/10) | 4.92 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 4.72/ 17.15 GFLOPS | Progress: (4/10) | 3.67 s
[Task 6/25] Current/Best: 8.84/ 17.15 GFLOPS | Progress: (8/10) | 6.38 s
[Task 6/25] Current/Best: 7.13/ 17.15 GFLOPS | Progress: (10/10) | 8.12 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 1.60/ 17.24 GFLOPS | Progress: (4/10) | 4.38 s
[Task 7/25] Current/Best: 14.76/ 23.20 GFLOPS | Progress: (8/10) | 6.01 s
[Task 7/25] Current/Best: 8.49/ 23.20 GFLOPS | Progress: (10/10) | 7.05 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 17.45/ 18.06 GFLOPS | Progress: (4/10) | 2.71 s
[Task 8/25] Current/Best: 17.69/ 18.06 GFLOPS | Progress: (8/10) | 9.09 s
[Task 8/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (10/10) | 10.42 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 12.03/ 18.02 GFLOPS | Progress: (4/10) | 7.68 s
[Task 9/25] Current/Best: 12.00/ 18.02 GFLOPS | Progress: (8/10) | 18.43 s
[Task 9/25] Current/Best: 22.69/ 22.69 GFLOPS | Progress: (10/10) | 19.40 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 10.44/ 18.27 GFLOPS | Progress: (4/10) | 3.83 s
[Task 10/25] Current/Best: 13.82/ 18.27 GFLOPS | Progress: (8/10) | 5.33 s
[Task 10/25] Current/Best: 13.72/ 18.27 GFLOPS | Progress: (10/10) | 6.43 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 9.01/ 23.56 GFLOPS | Progress: (4/10) | 3.04 s
[Task 11/25] Current/Best: 12.15/ 23.56 GFLOPS | Progress: (8/10) | 5.23 s
[Task 11/25] Current/Best: 15.20/ 23.56 GFLOPS | Progress: (10/10) | 6.22 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 13.71/ 15.70 GFLOPS | Progress: (4/10) | 3.89 s
[Task 12/25] Current/Best: 10.05/ 15.70 GFLOPS | Progress: (8/10) | 6.24 s
[Task 12/25] Current/Best: 6.51/ 15.70 GFLOPS | Progress: (10/10) | 7.46 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 15.74/ 16.83 GFLOPS | Progress: (4/10) | 3.07 s
[Task 13/25] Current/Best: 14.34/ 18.01 GFLOPS | Progress: (8/10) | 5.65 s
[Task 13/25] Current/Best: 22.20/ 22.20 GFLOPS | Progress: (10/10) | 6.69 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 19.38/ 19.39 GFLOPS | Progress: (4/10) | 2.78 s
[Task 14/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (8/10) | 6.63 s
[Task 14/25] Current/Best: 21.42/ 21.42 GFLOPS | Progress: (10/10) | 7.45 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (4/10) | 2.37 s
[Task 15/25] Current/Best: 11.79/ 21.91 GFLOPS | Progress: (8/10) | 4.89 s
[Task 15/25] Current/Best: 20.77/ 21.91 GFLOPS | Progress: (10/10) | 5.44 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (4/10) | 2.90 s
[Task 16/25] Current/Best: 7.54/ 21.17 GFLOPS | Progress: (8/10) | 5.81 s
[Task 16/25] Current/Best: 11.19/ 21.17 GFLOPS | Progress: (10/10) | 6.39 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 1.56/ 15.57 GFLOPS | Progress: (4/10) | 4.54 s
[Task 17/25] Current/Best: 16.38/ 23.08 GFLOPS | Progress: (8/10) | 6.95 s
[Task 17/25] Current/Best: 19.49/ 23.08 GFLOPS | Progress: (10/10) | 7.70 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 10.45/ 10.45 GFLOPS | Progress: (4/10) | 7.87 s
[Task 18/25] Current/Best: 22.26/ 22.26 GFLOPS | Progress: (8/10) | 9.58 s
[Task 18/25] Current/Best: 9.87/ 22.26 GFLOPS | Progress: (10/10) | 12.35 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 17.64/ 18.73 GFLOPS | Progress: (4/10) | 4.67 s
[Task 19/25] Current/Best: 12.05/ 21.18 GFLOPS | Progress: (8/10) | 9.43 s
[Task 19/25] Current/Best: 6.16/ 21.18 GFLOPS | Progress: (10/10) | 10.70 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 6.91/ 17.61 GFLOPS | Progress: (4/10) | 3.37 s
[Task 20/25] Current/Best: 16.91/ 17.61 GFLOPS | Progress: (8/10) | 5.88 s
[Task 20/25] Current/Best: 16.88/ 17.61 GFLOPS | Progress: (10/10) | 6.74 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 10.97/ 10.97 GFLOPS | Progress: (4/10) | 3.74 s Done.
-
[Task 21/25] Current/Best: 4.74/ 22.36 GFLOPS | Progress: (8/10) | 5.70 s
[Task 21/25] Current/Best: 16.04/ 22.36 GFLOPS | Progress: (10/10) | 6.39 s Done.
-
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 6.79/ 18.99 GFLOPS | Progress: (4/10) | 3.42 s
[Task 22/25] Current/Best: 2.69/ 18.99 GFLOPS | Progress: (8/10) | 5.90 s
[Task 22/25] Current/Best: 9.62/ 18.99 GFLOPS | Progress: (10/10) | 7.76 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 17.95/ 20.98 GFLOPS | Progress: (4/10) | 3.41 s
[Task 23/25] Current/Best: 14.30/ 20.98 GFLOPS | Progress: (8/10) | 5.62 s
[Task 23/25] Current/Best: 15.34/ 20.98 GFLOPS | Progress: (10/10) | 6.56 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 7.29/ 7.29 GFLOPS | Progress: (4/10) | 4.31 s
[Task 24/25] Current/Best: 2.51/ 7.29 GFLOPS | Progress: (8/10) | 18.77 s
[Task 24/25] Current/Best: 3.56/ 7.29 GFLOPS | Progress: (10/10) | 21.60 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 4.84/ 9.54 GFLOPS | Progress: (4/10) | 4.58 s
[Task 25/25] Current/Best: 5.73/ 9.54 GFLOPS | Progress: (8/10) | 5.94 s
[Task 25/25] Current/Best: 3.03/ 9.54 GFLOPS | Progress: (10/10) | 6.45 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 8.81/ 14.27 GFLOPS | Progress: (4/10) | 5.95 s
[Task 1/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (8/10) | 8.36 s
[Task 1/25] Current/Best: 1.93/ 21.22 GFLOPS | Progress: (10/10) | 10.48 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 11.98/ 16.80 GFLOPS | Progress: (4/10) | 3.65 s
[Task 2/25] Current/Best: 17.29/ 19.90 GFLOPS | Progress: (8/10) | 4.90 s
[Task 2/25] Current/Best: 20.16/ 20.16 GFLOPS | Progress: (10/10) | 5.58 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 9.88/ 16.60 GFLOPS | Progress: (4/10) | 3.74 s
[Task 3/25] Current/Best: 12.70/ 16.60 GFLOPS | Progress: (8/10) | 6.47 s
[Task 3/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (10/10) | 7.35 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 11.83/ 11.83 GFLOPS | Progress: (4/10) | 5.50 s
[Task 4/25] Current/Best: 3.87/ 16.77 GFLOPS | Progress: (8/10) | 8.51 s
[Task 4/25] Current/Best: 15.41/ 16.77 GFLOPS | Progress: (10/10) | 9.59 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 14.84/ 20.41 GFLOPS | Progress: (4/10) | 3.82 s
[Task 5/25] Current/Best: 3.50/ 20.41 GFLOPS | Progress: (8/10) | 6.11 s
[Task 5/25] Current/Best: 1.71/ 20.41 GFLOPS | Progress: (10/10) | 7.43 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 9.02/ 23.30 GFLOPS | Progress: (4/10) | 2.64 s
[Task 6/25] Current/Best: 13.18/ 23.30 GFLOPS | Progress: (8/10) | 5.39 s
[Task 6/25] Current/Best: 18.44/ 23.30 GFLOPS | Progress: (10/10) | 6.42 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 13.90/ 22.33 GFLOPS | Progress: (4/10) | 2.62 s
[Task 7/25] Current/Best: 14.69/ 22.38 GFLOPS | Progress: (8/10) | 4.55 s
[Task 7/25] Current/Best: 9.90/ 22.38 GFLOPS | Progress: (10/10) | 6.98 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 15.29/ 15.91 GFLOPS | Progress: (4/10) | 12.26 s
[Task 8/25] Current/Best: 16.59/ 19.47 GFLOPS | Progress: (8/10) | 14.43 s
[Task 8/25] Current/Best: 22.12/ 22.12 GFLOPS | Progress: (10/10) | 15.97 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 21.77/ 21.77 GFLOPS | Progress: (4/10) | 20.72 s
[Task 9/25] Current/Best: 17.27/ 21.77 GFLOPS | Progress: (8/10) | 22.61 s
[Task 9/25] Current/Best: 16.13/ 21.77 GFLOPS | Progress: (10/10) | 26.89 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 16.03/ 16.03 GFLOPS | Progress: (4/10) | 2.32 s
[Task 10/25] Current/Best: 4.95/ 22.79 GFLOPS | Progress: (8/10) | 4.13 s
[Task 10/25] Current/Best: 4.17/ 22.79 GFLOPS | Progress: (10/10) | 5.10 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 17.24/ 23.42 GFLOPS | Progress: (4/10) | 2.87 s
[Task 11/25] Current/Best: 15.91/ 23.62 GFLOPS | Progress: (8/10) | 5.01 s
[Task 11/25] Current/Best: 19.37/ 23.62 GFLOPS | Progress: (10/10) | 5.86 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 6.28/ 15.64 GFLOPS | Progress: (4/10) | 9.37 s
[Task 12/25] Current/Best: 6.38/ 17.64 GFLOPS | Progress: (8/10) | 12.23 s
[Task 12/25] Current/Best: 4.86/ 17.64 GFLOPS | Progress: (10/10) | 13.44 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 14.96/ 23.18 GFLOPS | Progress: (4/10) | 2.96 s
[Task 13/25] Current/Best: 9.35/ 23.18 GFLOPS | Progress: (8/10) | 6.13 s
[Task 13/25] Current/Best: 9.10/ 23.18 GFLOPS | Progress: (10/10) | 7.76 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 9.06/ 18.71 GFLOPS | Progress: (4/10) | 6.12 s
[Task 14/25] Current/Best: 10.61/ 18.71 GFLOPS | Progress: (8/10) | 8.61 s
[Task 14/25] Current/Best: 12.55/ 18.71 GFLOPS | Progress: (10/10) | 9.84 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+ Done.
+
[Task 15/25] Current/Best: 7.61/ 23.93 GFLOPS | Progress: (4/10) | 3.76 s
[Task 15/25] Current/Best: 15.21/ 23.93 GFLOPS | Progress: (8/10) | 5.14 s
[Task 15/25] Current/Best: 18.45/ 23.93 GFLOPS | Progress: (10/10) | 5.84 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 15.70/ 19.16 GFLOPS | Progress: (4/10) | 2.62 s
[Task 16/25] Current/Best: 9.95/ 19.16 GFLOPS | Progress: (8/10) | 5.91 s
[Task 16/25] Current/Best: 16.27/ 19.16 GFLOPS | Progress: (10/10) | 6.88 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 18.39/ 18.39 GFLOPS | Progress: (4/10) | 2.56 s
[Task 17/25] Current/Best: 1.56/ 18.58 GFLOPS | Progress: (8/10) | 6.28 s
[Task 17/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (10/10) | 6.96 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 6.50/ 16.25 GFLOPS | Progress: (4/10) | 4.49 s
[Task 18/25] Current/Best: 16.04/ 18.48 GFLOPS | Progress: (8/10) | 6.05 s
[Task 18/25] Current/Best: 9.56/ 18.48 GFLOPS | Progress: (10/10) | 7.59 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (4/10) | 2.94 s
[Task 19/25] Current/Best: 10.85/ 22.60 GFLOPS | Progress: (8/10) | 7.92 s
[Task 19/25] Current/Best: 15.98/ 22.60 GFLOPS | Progress: (10/10) | 8.82 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 7.22/ 13.42 GFLOPS | Progress: (4/10) | 4.39 s
[Task 20/25] Current/Best: 2.51/ 17.11 GFLOPS | Progress: (8/10) | 6.61 s
[Task 20/25] Current/Best: 1.57/ 17.11 GFLOPS | Progress: (10/10) | 8.96 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 13.79/ 20.24 GFLOPS | Progress: (4/10) | 2.60 s
[Task 21/25] Current/Best: 17.16/ 20.24 GFLOPS | Progress: (8/10) | 4.12 s
[Task 21/25] Current/Best: 12.08/ 20.24 GFLOPS | Progress: (10/10) | 5.26 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+ Done.
+ Done.
+
[Task 22/25] Current/Best: 5.93/ 19.33 GFLOPS | Progress: (4/10) | 3.80 s
[Task 22/25] Current/Best: 9.71/ 19.33 GFLOPS | Progress: (8/10) | 6.20 s
[Task 22/25] Current/Best: 16.48/ 19.33 GFLOPS | Progress: (10/10) | 6.79 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 16.20/ 20.92 GFLOPS | Progress: (4/10) | 3.67 s
[Task 23/25] Current/Best: 11.53/ 21.75 GFLOPS | Progress: (8/10) | 5.79 s
[Task 23/25] Current/Best: 17.66/ 21.75 GFLOPS | Progress: (10/10) | 7.09 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (4/10) | 88.02 s
[Task 24/25] Current/Best: 3.96/ 3.96 GFLOPS | Progress: (8/10) | 101.96 s
[Task 24/25] Current/Best: 1.56/ 3.96 GFLOPS | Progress: (10/10) | 113.65 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 6.59/ 8.43 GFLOPS | Progress: (4/10) | 5.82 s Done.
+
[Task 25/25] Current/Best: 8.82/ 8.82 GFLOPS | Progress: (8/10) | 6.97 s
[Task 25/25] Current/Best: 7.60/ 8.82 GFLOPS | Progress: (10/10) | 7.48 s Done.
@@ -595,7 +596,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356379
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -648,8 +649,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 430.49108314999904, 'median': 430.111272649998, 'std': 0.9557213800757237}
- unoptimized: {'mean': 498.4630057199991, 'median': 498.29967405000275, 'std': 0.5841999958077553}
+ optimized: {'mean': 437.42848505999973, 'median': 437.4217916500015, 'std': 0.7323361024402074}
+ unoptimized: {'mean': 491.0830640700011, 'median': 491.01350355000477, 'std': 0.4615301791043869}
@@ -669,7 +670,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 43.192 seconds)
+ **Total running time of the script:** ( 8 minutes 30.565 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 f425657..5517873 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.26e-07 secs/op
+ 1.288e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index c129f4c..21221cf 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -230,7 +230,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x193f69d0)), stage(b, placeholder(b, 0x19bc37c0)), 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, 0x1985d970)), stage(b, placeholder(b, 0x43dc560)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 5264fdc..75f9a95 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**09:24.662** total execution time for **tutorial** files:
+**11:36.363** total execution time for **tutorial** files:
-- **06:43.192**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **00:59.552**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:59.163**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:26.648**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:13.760**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.190**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.730**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.222**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.053**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.053**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.050**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.048**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **08:30.565**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:14.937**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **01:02.135**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:25.939**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:20.680**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:01.090**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.693**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.200**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.037**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.030**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.030**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.029**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 4b3994c..3dff1ca 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -334,7 +334,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000006
@@ -436,10 +436,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.68407999998999e-06 1.0
- naive 5.856e-06 0.7620951369594836
- parallel 6.9837000000000006e-06 0.908853109286876
- vector 2.4532300000000002e-05 3.192613819745755
+ numpy 8.134429999699932e-06 1.0
+ naive 5.8989e-06 0.7251768102027558
+ parallel 6.0761999999999995e-06 0.7469730516119928
+ vector 2.45311e-05 3.0157122257988473
@@ -828,7 +828,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019290
+ Numpy running time: 0.017880
@@ -884,7 +884,7 @@ optimizations.
.. code-block:: none
- none: 3.258723
+ none: 3.510692
@@ -982,7 +982,7 @@ schedule.
.. code-block:: none
- blocking: 0.329134
+ blocking: 0.306112
@@ -1008,8 +1008,8 @@ internal representation and compare it to the original:
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x.outer: int32, 0, 32) {
@@ -1073,11 +1073,11 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.349938
+ vectorization: 0.339071
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x.outer: int32, 0, 32) {
@@ -1144,7 +1144,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.121660
+ loop permutation: 0.114924
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1240,7 +1240,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108962
+ array packing: 0.109074
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1330,11 +1330,11 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110613
+ block caching: 0.110414
@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], []),
- C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
allocate(packedB: Pointer(global float32x32), float32x32, [32768]), storage_scope = global;
@@ -1413,7 +1413,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.144784
+ parallelization: 0.144231
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1491,13 +1491,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2587225122 1.0
- blocking 0.3291344043 0.10100105273394319
- vectorization 0.3499376062 0.10738490463361153
- loop permutation 0.12165952850000002 0.037333503556848203
- array packing 0.1089624357 0.033437162965569055
- block caching 0.11061333660000001 0.03394377280848124
- parallelization 0.144783868 0.04442963997638903
+ none 3.5106921898000003 1.0
+ blocking 0.3061121634 0.0871942474163304
+ vectorization 0.3390714418 0.09658250381082725
+ loop permutation 0.11492392359999999 0.03273540298802074
+ array packing 0.10907418399999999 0.031069139105075975
+ block caching 0.11041368359999999 0.03145068767942601
+ parallelization 0.1442312776 0.041083430218989574
@@ -1532,6 +1532,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 2.135 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index ba8a2f4..ba2e702 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-532b2b4a622b1fae0bd7aac66a2fb8ada8c49d7f
+14084f4c341aae5633b34d11748d3c590237824e
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index d369e69..9253087 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip5c40c6be-1325-4f32-9a67-31ced66af4ff from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe6ad9fc2-ee97-499f-a344-eef7c606f586 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_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 8061144..0a3567f 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -449,7 +449,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.190 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.102 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.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_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index daf41a0..6c1cf67 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,10 +387,21 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 25%|##5 | 11.2M/44.7M [00:00<00:00, 118MB/s]
- 60%|###### | 26.9M/44.7M [00:00<00:00, 145MB/s]
- 91%|#########1| 40.7M/44.7M [00:00<00:00, 112MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 116MB/s]
+ 7%|6 | 3.12M/44.7M [00:00<00:01, 31.9MB/s]
+ 14%|#3 | 6.16M/44.7M [00:00<00:01, 28.9MB/s]
+ 20%|## | 8.94M/44.7M [00:00<00:01, 26.5MB/s]
+ 27%|##7 | 12.2M/44.7M [00:00<00:01, 27.9MB/s]
+ 34%|###3 | 15.0M/44.7M [00:00<00:01, 28.3MB/s]
+ 40%|###9 | 17.7M/44.7M [00:00<00:01, 26.8MB/s]
+ 45%|####5 | 20.3M/44.7M [00:00<00:01, 18.0MB/s]
+ 50%|##### | 22.5M/44.7M [00:01<00:01, 19.2MB/s]
+ 59%|#####8 | 26.2M/44.7M [00:01<00:00, 23.7MB/s]
+ 64%|######4 | 28.7M/44.7M [00:01<00:00, 22.5MB/s]
+ 74%|#######4 | 33.1M/44.7M [00:01<00:00, 28.0MB/s]
+ 82%|########1 | 36.5M/44.7M [00:01<00:00, 29.9MB/s]
+ 88%|########8 | 39.5M/44.7M [00:01<00:00, 29.2MB/s]
+ 95%|#########5| 42.4M/44.7M [00:01<00:00, 27.0MB/s]
+100%|##########| 44.7M/44.7M [00:01<00:00, 25.6MB/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 2fca8b0..961bb79 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -611,7 +611,7 @@ 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 13.982 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.945 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download 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 2f11629..d921da0 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<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>05:44.943</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:44.574</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:13.982</strong>: <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></li>
-<li><p><strong>01:07.190</strong>: <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></li>
-<li><p><strong>00:57.195</strong>: <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></li>
-<li><p><strong>00:41.684</strong>: <a class="reference internal" href="from_caffe2.html#sphx-glr-how-to-compile-models-from-caffe2-py"><span class="std std-ref">Compile Caffe2 Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_caffe2.py</span></code>)</p></li>
-<li><p><strong>00:25.248</strong>: <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></li>
-<li><p><strong>00:21.677</strong>: <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></li>
-<li><p><strong>00:21.566</strong>: <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></li>
-<li><p><strong>00:19.613</strong>: <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></li>
-<li><p><strong>00:14.138</strong>: <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></li>
-<li><p><strong>00:02.650</strong>: <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></li>
+<li><p><strong>01:20.102</strong>: <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></li>
+<li><p><strong>01:06.945</strong>: <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></li>
+<li><p><strong>00:54.647</strong>: <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></li>
+<li><p><strong>00:41.010</strong>: <a class="reference internal" href="from_caffe2.html#sphx-glr-how-to-compile-models-from-caffe2-py"><span class="std std-ref">Compile Caffe2 Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_caffe2.py</span></code>)</p></li>
+<li><p><strong>00:24.513</strong>: <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></li>
+<li><p><strong>00:20.581</strong>: <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></li>
+<li><p><strong>00:20.567</strong>: <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></li>
+<li><p><strong>00:20.071</strong>: <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></li>
+<li><p><strong>00:13.836</strong>: <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></li>
+<li><p><strong>00:02.304</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 9c2cf4b..4c976a4 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3047 16.3103 16.4043 16.1583 0.0662
+ 15.6985 15.6811 15.8491 15.5790 0.0836
</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 3d9aed3..add4a70 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,19 +409,61 @@ 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]
- 1%|1 | 1.80M/170M [00:00<00:09, 18.8MB/s]
- 2%|2 | 3.62M/170M [00:00<00:09, 18.6MB/s]
- 9%|9 | 15.4M/170M [00:00<00:02, 66.1MB/s]
- 20%|#9 | 33.6M/170M [00:00<00:01, 115MB/s]
- 31%|### | 51.8M/170M [00:00<00:00, 142MB/s]
- 39%|###9 | 67.1M/170M [00:00<00:00, 147MB/s]
- 49%|####9 | 83.4M/170M [00:00<00:00, 155MB/s]
- 58%|#####7 | 98.2M/170M [00:00<00:00, 152MB/s]
- 66%|######6 | 113M/170M [00:00<00:00, 148MB/s]
- 75%|#######5 | 128M/170M [00:01<00:00, 151MB/s]
- 84%|########3 | 142M/170M [00:01<00:00, 151MB/s]
- 93%|#########2| 157M/170M [00:01<00:00, 154MB/s]
-100%|##########| 170M/170M [00:01<00:00, 136MB/s]
+ 3%|2 | 4.68M/170M [00:00<00:03, 49.1MB/s]
+ 6%|5 | 9.36M/170M [00:00<00:04, 38.7MB/s]
+ 8%|7 | 13.3M/170M [00:00<00:04, 39.6MB/s]
+ 11%|# | 18.3M/170M [00:00<00:03, 44.5MB/s]
+ 13%|#3 | 22.7M/170M [00:00<00:03, 41.4MB/s]
+ 16%|#5 | 26.9M/170M [00:00<00:03, 42.2MB/s]
+ 18%|#8 | 31.0M/170M [00:00<00:04, 33.4MB/s]
+ 20%|## | 34.4M/170M [00:01<00:05, 28.3MB/s]
+ 22%|##2 | 37.4M/170M [00:01<00:05, 25.0MB/s]
+ 24%|##3 | 40.0M/170M [00:01<00:05, 22.9MB/s]
+ 25%|##4 | 42.3M/170M [00:01<00:06, 20.4MB/s]
+ 26%|##6 | 44.4M/170M [00:01<00:08, 16.4MB/s]
+ 27%|##7 | 46.6M/170M [00:01<00:07, 17.7MB/s]
+ 29%|##8 | 48.5M/170M [00:02<00:07, 16.0MB/s]
+ 31%|###1 | 53.2M/170M [00:02<00:05, 23.2MB/s]
+ 33%|###3 | 56.9M/170M [00:02<00:04, 26.8MB/s]
+ 35%|###5 | 59.8M/170M [00:02<00:04, 26.8MB/s]
+ 37%|###7 | 63.1M/170M [00:02<00:03, 29.0MB/s]
+ 39%|###8 | 66.1M/170M [00:02<00:03, 29.2MB/s]
+ 41%|#### | 69.2M/170M [00:02<00:03, 30.1MB/s]
+ 42%|####2 | 72.1M/170M [00:02<00:04, 21.8MB/s]
+ 44%|####3 | 74.7M/170M [00:02<00:04, 22.8MB/s]
+ 45%|####5 | 77.2M/170M [00:03<00:04, 22.1MB/s]
+ 47%|####7 | 80.1M/170M [00:03<00:03, 23.6MB/s]
+ 49%|####8 | 82.5M/170M [00:03<00:04, 21.6MB/s]
+ 50%|##### | 85.8M/170M [00:03<00:03, 24.5MB/s]
+ 52%|#####1 | 88.2M/170M [00:03<00:03, 22.2MB/s]
+ 54%|#####3 | 91.1M/170M [00:03<00:03, 24.1MB/s]
+ 55%|#####5 | 93.9M/170M [00:03<00:03, 25.0MB/s]
+ 57%|#####7 | 97.0M/170M [00:03<00:02, 27.1MB/s]
+ 59%|#####8 | 99.7M/170M [00:04<00:02, 25.5MB/s]
+ 60%|###### | 102M/170M [00:04<00:02, 25.6MB/s]
+ 62%|######1 | 105M/170M [00:04<00:02, 25.9MB/s]
+ 63%|######3 | 107M/170M [00:04<00:02, 23.5MB/s]
+ 65%|######4 | 110M/170M [00:04<00:02, 23.5MB/s]
+ 67%|######6 | 113M/170M [00:04<00:02, 26.7MB/s]
+ 69%|######8 | 117M/170M [00:04<00:01, 30.9MB/s]
+ 71%|####### | 120M/170M [00:04<00:01, 27.7MB/s]
+ 72%|#######2 | 123M/170M [00:05<00:02, 21.5MB/s]
+ 74%|#######3 | 125M/170M [00:05<00:02, 18.8MB/s]
+ 75%|#######5 | 127M/170M [00:05<00:02, 19.0MB/s]
+ 76%|#######6 | 129M/170M [00:05<00:02, 19.0MB/s]
+ 78%|#######8 | 133M/170M [00:05<00:01, 22.1MB/s]
+ 80%|######## | 136M/170M [00:05<00:01, 25.0MB/s]
+ 82%|########1 | 138M/170M [00:05<00:01, 24.7MB/s]
+ 83%|########2 | 141M/170M [00:05<00:01, 24.4MB/s]
+ 85%|########4 | 144M/170M [00:05<00:01, 25.0MB/s]
+ 86%|########5 | 146M/170M [00:06<00:01, 22.5MB/s]
+ 88%|########8 | 150M/170M [00:06<00:00, 28.0MB/s]
+ 90%|######### | 153M/170M [00:06<00:00, 29.8MB/s]
+ 92%|#########2| 156M/170M [00:06<00:00, 30.2MB/s]
+ 94%|#########4| 160M/170M [00:06<00:00, 33.3MB/s]
+ 96%|#########6| 164M/170M [00:06<00:00, 28.5MB/s]
+ 99%|#########8| 168M/170M [00:06<00:00, 32.7MB/s]
+100%|##########| 170M/170M [00:06<00:00, 26.1MB/s]
/usr/local/lib/python3.7/dist-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3702: 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).
@@ -516,7 +558,7 @@ 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 11.492 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 5.785 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download 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 7f0754f..91dc35f 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,9 +450,13 @@ 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]
- 30%|##9 | 4.06M/13.6M [00:00<00:00, 39.3MB/s]
- 81%|######## | 11.0M/13.6M [00:00<00:00, 57.4MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 56.1MB/s]
+ 5%|5 | 728k/13.6M [00:00<00:01, 7.13MB/s]
+ 10%|# | 1.40M/13.6M [00:00<00:01, 6.71MB/s]
+ 32%|###1 | 4.32M/13.6M [00:00<00:00, 15.1MB/s]
+ 49%|####9 | 6.68M/13.6M [00:00<00:00, 16.8MB/s]
+ 61%|###### | 8.23M/13.6M [00:00<00:00, 13.8MB/s]
+ 99%|#########8| 13.4M/13.6M [00:00<00:00, 24.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 18.9MB/s]
</pre></div>
</div>
</div>
@@ -545,7 +549,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<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)
- 90.2868 90.2253 92.9443 90.0490 0.3068
+ 90.5035 90.1648 109.1200 89.8791 2.0112
</pre></div>
</div>
<div class="admonition note">
@@ -584,7 +588,7 @@ 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 7.091 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.925 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download 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 d3611b3..94003fe 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<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)
- 120.3628 120.3502 122.3226 119.6968 0.4207
+ 117.9394 117.9172 119.7118 116.7910 0.5408
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 54.164 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.985 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download 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 7d22b11..b6c1018 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ 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 21.133 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.828 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download 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 5b354bd..3dcebd3 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,23 +415,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|3 | 5270/132723 [00:00<00:02, 52692.14KB/s]
- 10%|# | 13310/132723 [00:00<00:01, 68984.31KB/s]
- 16%|#6 | 21380/132723 [00:00<00:01, 74329.43KB/s]
- 22%|##2 | 29424/132723 [00:00<00:01, 76739.12KB/s]
- 28%|##8 | 37426/132723 [00:00<00:01, 77919.49KB/s]
- 34%|###4 | 45465/132723 [00:00<00:01, 78754.77KB/s]
- 40%|#### | 53444/132723 [00:00<00:01, 79091.30KB/s]
- 46%|####6 | 61478/132723 [00:00<00:00, 79487.43KB/s]
- 52%|#####2 | 69536/132723 [00:00<00:00, 79826.31KB/s]
- 58%|#####8 | 77519/132723 [00:01<00:00, 79781.85KB/s]
- 64%|######4 | 85498/132723 [00:01<00:00, 79725.87KB/s]
- 70%|####### | 93542/132723 [00:01<00:00, 79940.29KB/s]
- 77%|#######6 | 101537/132723 [00:01<00:00, 79866.70KB/s]
- 83%|########2 | 109524/132723 [00:01<00:00, 79747.53KB/s]
- 89%|########8 | 117520/132723 [00:01<00:00, 79808.33KB/s]
- 95%|#########4| 125573/132723 [00:01<00:00, 80023.86KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 78522.26KB/s]
+ 3%|3 | 3983/132723 [00:00<00:03, 39827.95KB/s]
+ 7%|7 | 9755/132723 [00:00<00:02, 50347.76KB/s]
+ 14%|#3 | 18308/132723 [00:00<00:01, 66402.34KB/s]
+ 20%|## | 26941/132723 [00:00<00:01, 74264.35KB/s]
+ 27%|##6 | 35534/132723 [00:00<00:01, 78469.26KB/s]
+ 33%|###3 | 44164/132723 [00:00<00:01, 81122.70KB/s]
+ 40%|###9 | 52596/132723 [00:00<00:00, 82166.71KB/s]
+ 46%|####6 | 61270/132723 [00:00<00:00, 83619.40KB/s]
+ 53%|#####2 | 69956/132723 [00:00<00:00, 84629.99KB/s]
+ 59%|#####9 | 78645/132723 [00:01<00:00, 85326.23KB/s]
+ 66%|######5 | 87309/132723 [00:01<00:00, 85726.18KB/s]
+ 72%|#######2 | 95913/132723 [00:01<00:00, 85820.36KB/s]
+ 79%|#######8 | 104542/132723 [00:01<00:00, 85956.19KB/s]
+ 85%|########5 | 113270/132723 [00:01<00:00, 86354.67KB/s]
+ 92%|#########1| 121906/132723 [00:01<00:00, 86275.95KB/s]
+ 98%|#########8| 130534/132723 [00:01<00:00, 86060.87KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 81502.77KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -471,7 +471,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.546 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 18.803 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download 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 0192dd4..cc47cae 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>10:53.712</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:27.992</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:11.492</strong>: <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></li>
-<li><p><strong>02:28.546</strong>: <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></li>
-<li><p><strong>01:54.164</strong>: <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></li>
-<li><p><strong>01:21.133</strong>: <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></li>
-<li><p><strong>01:07.091</strong>: <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></li>
-<li><p><strong>00:29.133</strong>: <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></li>
-<li><p><strong>00:21.937</strong>: <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></li>
-<li><p><strong>00:00.216</strong>: <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></li>
+<li><p><strong>03:05.785</strong>: <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></li>
+<li><p><strong>02:18.803</strong>: <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></li>
+<li><p><strong>01:52.985</strong>: <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></li>
+<li><p><strong>01:17.828</strong>: <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></li>
+<li><p><strong>01:03.925</strong>: <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></li>
+<li><p><strong>00:27.271</strong>: <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></li>
+<li><p><strong>00:21.201</strong>: <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></li>
+<li><p><strong>00:00.195</strong>: <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></li>
</ul>
</div>
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 63ce69a..0789e04 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -588,7 +588,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipe4018526-8958-4625-b745-14a855bac435 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.zip19c3c456-218b-4d24-a9cf-8979116f4484 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>
@@ -650,7 +650,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registerd for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/low_level_custom_pass.html b/docs/how_to/extend_tvm/low_level_custom_pass.html
index 7d6d5c7..2bb43e3 100644
--- a/docs/how_to/extend_tvm/low_level_custom_pass.html
+++ b/docs/how_to/extend_tvm/low_level_custom_pass.html
@@ -375,8 +375,8 @@ our customized lowering pass to manipulate the IR directly instead of using sche
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(a_1: handle, b_1: handle, c_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {c: Buffer(c_2: Pointer(float32), float32, [128], []),
- a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ buffers = {a: Buffer(a_2: Pointer(float32), float32, [128], []),
+ c: Buffer(c_2: Pointer(float32), float32, [128], []),
b: Buffer(b_2: Pointer(float32), float32, [128], [])}
buffer_map = {a_1: a, b_1: b, c_1: c} {
for (i: int32, 0, 128) {
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index af9d1ac..fd25d3d 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<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>00:39.612</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.594</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:35.902</strong>: <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></li>
-<li><p><strong>00:02.359</strong>: <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></li>
-<li><p><strong>00:01.130</strong>: <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></li>
-<li><p><strong>00:00.221</strong>: <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></li>
+<li><p><strong>00:34.093</strong>: <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></li>
+<li><p><strong>00:02.239</strong>: <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></li>
+<li><p><strong>00:01.065</strong>: <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></li>
+<li><p><strong>00:00.197</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 79bf995..2ab25ba 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6382us [6382us] (45.72%; 45.72%)
-FoldScaleAxis: 7578us [2us] (54.28%; 54.28%)
- FoldConstant: 7576us [1573us] (54.27%; 99.97%)
- InferType: 6003us [6003us] (43.00%; 79.24%)
+InferType: 6014us [6014us] (44.76%; 44.76%)
+FoldScaleAxis: 7422us [2us] (55.24%; 55.24%)
+ FoldConstant: 7420us [1499us] (55.23%; 99.97%)
+ InferType: 5922us [5922us] (44.07%; 79.80%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6268us [6268us] (45.31%; 45.31%)
-FoldScaleAxis: 7565us [2us] (54.69%; 54.69%)
- FoldConstant: 7563us [1589us] (54.67%; 99.97%)
- InferType: 5973us [5973us] (43.18%; 78.98%)
+InferType: 6139us [6139us] (44.82%; 44.82%)
+FoldScaleAxis: 7557us [2us] (55.18%; 55.18%)
+ FoldConstant: 7555us [1655us] (55.16%; 99.97%)
+ InferType: 5900us [5900us] (43.08%; 78.09%)
</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 c0ef3da..b91a02e 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 43.128546 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.139155 ms
</pre></div>
</div>
<div class="sphx-glr-footer class 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 37b15de..8d66c34 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -876,7 +876,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.665528 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.634120 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 d81bd44..37d6e53 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019299
-Baseline: 3.253213
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017750
+Baseline: 3.443008
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -493,7 +493,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.314582
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.303428
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -503,8 +503,8 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (m.outer: int32, 0, 32) {
@@ -561,7 +561,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.346832
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332963
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -571,8 +571,8 @@ vastly.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (m.outer: int32, 0, 32) {
@@ -623,7 +623,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.119707
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114610
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -707,7 +707,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111440
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110934
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -794,7 +794,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111517
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111276
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -885,7 +885,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146105
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144939
</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 61a9b09..719be74 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.226</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.055</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.461</strong>: <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></li>
-<li><p><strong>00:01.524</strong>: <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></li>
-<li><p><strong>00:01.241</strong>: <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></li>
+<li><p><strong>00:32.398</strong>: <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></li>
+<li><p><strong>00:01.412</strong>: <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></li>
+<li><p><strong>00:01.245</strong>: <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></li>
</ul>
</div>
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 d253f9d..89131e9 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<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>05:12.234</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>04:49.359</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:25.299</strong>: <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></li>
-<li><p><strong>01:21.536</strong>: <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></li>
-<li><p><strong>00:41.142</strong>: <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></li>
-<li><p><strong>00:26.725</strong>: <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></li>
-<li><p><strong>00:08.863</strong>: <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></li>
-<li><p><strong>00:08.669</strong>: <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></li>
+<li><p><strong>02:16.909</strong>: <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></li>
+<li><p><strong>01:19.027</strong>: <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></li>
+<li><p><strong>00:40.003</strong>: <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></li>
+<li><p><strong>00:16.964</strong>: <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></li>
+<li><p><strong>00:08.273</strong>: <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></li>
+<li><p><strong>00:08.183</strong>: <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></li>
</ul>
</div>
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 2eada2b..69ad04d 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
@@ -469,63 +469,226 @@ cooperative fetching, unrolling and operator fusion.</p>
data: Buffer(data_2: Pointer(float32), float32, [25088], []),
kernel: Buffer(kernel_2: Pointer(float32), float32, [2359296], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 224;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [84]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [192]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ 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" = 112 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[1] = 0f32
for (rc.outer.outer: int32, 0, 128) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*36)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [84], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer) < 8)) && (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(threadId [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 28), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[((((((rc.outer.outer*196) + (floordiv((threadIdx.x_1 + 56), 3)*7)) + (ry.outer.ou [...]
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [192], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 12), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 12), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((floordiv(blockIdx.x, 7)*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 12), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((((floordiv(blockIdx.x, 7)*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 12), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 12)]))
- 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)*24) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 13)]))
- 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)*24) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 43)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 43)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 44)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 44)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*3) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*24) + 23)]))
+ let cse_var_1: int32 = (rc.outer.outer*36)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[(threadIdx.x_1*36)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 1)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 2)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 3)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 5)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 4)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 4)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 5)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 3)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 6)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 2)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 7)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) - 1)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 8)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 9)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 10)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 11)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 12)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 5)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 13)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 4)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 14)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 3)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 15)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 2)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 16)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 1), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 1), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 1), 3)*7)) - 1)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 17)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 18)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 19)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 20)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 21)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 5)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 22)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 4)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 23)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 3)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 24)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 2)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 25)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*4) + 2), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv(((threadIdx.x_1*4) + 2), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod(((threadIdx.x_1*4) + 2), 3)*7)) - 1)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 26)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 27)] = 0f32
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 28)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 42)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 29)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 43)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 30)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 44)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 31)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 45)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 32)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 46)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 33)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 47)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 34)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1*4), 3)) < 8)), data[(((((rc.outer.outer*196) + (floordiv((threadIdx.x_1*4), 3)*49)) + (floormod(blockIdx.x, 7)*7)) + (floormod((threadIdx.x_1*4), 3)*7)) + 48)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 3), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*36) + 35)] = 0f32
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ 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" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv(floordiv(threadIdx.x_2, 4), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
}
}
for (i1.inner: int32, 0, 2) {
- compute[(((((floordiv(blockIdx.x, 7)*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((floordiv(blockIdx.x, 7)*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((floordiv(blockIdx.x, 7)*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -563,7 +726,7 @@ cooperative fetching, unrolling and operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.414 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.439 ms
</pre></div>
</div>
</div>
@@ -595,34 +758,34 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_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=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=8)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -642,14 +805,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=36)
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=56)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -667,54 +830,211 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[2];
- __shared__ float pad_temp_shared[84];
- __shared__ float kernel_shared[192];
+ __shared__ float pad_temp_shared[108];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.0000 [...]
- if (((int)threadIdx.x) < 28) {
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 56) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) [...]
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 24) {
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- }
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 43)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 43)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 44)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 44)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 3) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + 23)]));
+ __syncthreads();
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[(((int)threadIdx.x) * 36)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 1)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 2)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 3)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 5)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 4)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 4)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 5)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 3)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 6)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 2)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 7)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 8)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 9)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 10)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 11)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 12)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 5)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 13)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 4)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 14)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 3)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 15)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 2)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 16)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 1) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 1) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 1) % 3) * 7)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 17)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 18)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 19)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 20)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 21)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 5)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 22)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 4)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 23)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 3)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 24)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 2)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 25)] = (((1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 4) + 2) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 4) + 2) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + ((((((int)threadIdx.x) * 4) + 2) % 3) * 7)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 26)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 27)] = 0.000000e+00f;
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 28)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 42)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 29)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 43)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 30)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 44)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 31)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 45)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 32)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 46)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 33)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 47)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 34)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 4) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 4) / 3) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) % 3) * 7)) + 48)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 3) {
+ pad_temp_shared[((((int)threadIdx.x) * 36) + 35)] = 0.000000e+00f;
+ }
+ 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) + 112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 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))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 12) % 36))];
+ 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))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 20) % 36))];
+ 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) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ 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))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 129024)];
+ 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))];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -752,7 +1072,7 @@ 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> ( 2 minutes 25.299 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 16.909 seconds)</p>
<div class="sphx-glr-footer class 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 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 6a68c95..f39e06c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -876,7 +876,7 @@ 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)
- 9.7643 9.7568 9.7889 9.7473 0.0178
+ 9.9811 9.9866 10.0053 9.9513 0.0224
</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 16f2651..df1c92f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -895,7 +895,7 @@ 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)
- 764.3591 761.8650 769.4652 761.7469 3.6109
+ 761.2881 762.2861 764.8818 756.6965 3.4153
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.536 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.027 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download 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 a5ca8b8..9979f00 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -593,37 +593,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Lowered TIR:
@main = primfn(placeholder_5: handle, placeholder_6: handle, placeholder_7: handle, placeholder_8: handle, placeholder_9: handle, compute_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {placeholder_4: Buffer(placeholder_10: Pointer(int32), int32, [4916], []),
- placeholder_3: Buffer(placeholder_11: Pointer(float32), float32, [32768], []),
- compute: Buffer(compute_2: Pointer(float32), float32, [65536], []),
- placeholder: Buffer(placeholder_12: Pointer(float32), float32, [65536], []),
- placeholder_2: Buffer(placeholder_13: Pointer(float32), float32, [78656], []),
- placeholder_1: Buffer(placeholder_14: Pointer(int32), int32, [33], [])}
- buffer_map = {placeholder_9: placeholder, placeholder_8: placeholder_1, placeholder_6: placeholder_2, compute_1: compute, placeholder_5: placeholder_3, placeholder_7: placeholder_4} {
- allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [4096], [])[((((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ buffers = {placeholder_3: Buffer(placeholder_10: Pointer(float32), float32, [78656], []),
+ placeholder_4: Buffer(placeholder_11: Pointer(int32), int32, [4916], []),
+ placeholder_2: Buffer(placeholder_12: Pointer(float32), float32, [65536], []),
+ placeholder_1: Buffer(placeholder_13: Pointer(float32), float32, [32768], []),
+ placeholder: Buffer(placeholder_14: Pointer(int32), int32, [33], []),
+ compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
+ buffer_map = {placeholder_8: placeholder, compute_1: compute, placeholder_5: placeholder_1, placeholder_9: placeholder_2, placeholder_6: placeholder_3, placeholder_7: placeholder_4} {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = (i.inner.init*16)
+ {
+ compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_1[(cse_var_1 + 1)] - placeholder_1[cse_var_1])) {
- for (i.inner: int32, 0, 32) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_2[(((placeholder_1[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_3[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_4[(placeholder_1[cse_var_3] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder[(cse_var_2 + 1)] - placeholder[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_20: int32 = (i.inner*16)
+ let cse_var_19: int32 = (elem_idx*16)
+ let cse_var_18: int32 = (cse_var_20 + 10)
+ let cse_var_17: int32 = (cse_var_20 + 11)
+ let cse_var_16: int32 = (cse_var_20 + 12)
+ let cse_var_15: int32 = (cse_var_20 + 13)
+ let cse_var_14: int32 = (cse_var_20 + 14)
+ let cse_var_13: int32 = (cse_var_20 + 15)
+ let cse_var_12: int32 = (cse_var_20 + 2)
+ let cse_var_11: int32 = (cse_var_20 + 3)
+ let cse_var_10: int32 = (cse_var_20 + 4)
+ let cse_var_9: int32 = (cse_var_20 + 5)
+ let cse_var_8: int32 = (cse_var_20 + 6)
+ let cse_var_7: int32 = (cse_var_20 + 7)
+ let cse_var_6: int32 = (cse_var_20 + 8)
+ let cse_var_5: int32 = (cse_var_20 + 9)
+ let cse_var_4: int32 = (cse_var_20 + 1)
+ let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.inner*256))
+ {
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_3[((placeholder[cse_var_21]*16) + cse_var_19)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 1)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 2)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 3)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 4)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 5)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 6)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 7)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 8)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 9)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 10)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 11)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 12)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 13)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 14)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_3[(((placeholder[cse_var_21]*16) + cse_var_19) + 15)]*max(placeholder_1[(cse_var_3 + placeholder_4[(placeholder[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
- }
- for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((i0.inner*512) + (i1.outer*32)) + i1.inner)
- compute[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder[cse_var_4]), 0f32)
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_22, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_2[ramp(cse_var_22, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -662,7 +705,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.488 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.925 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 4bfb2fe..cc7e333 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:45.031</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.255</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.084</strong>: <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></li>
-<li><p><strong>00:00.246</strong>: <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></li>
-<li><p><strong>00:00.234</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
-<li><p><strong>00:00.234</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
-<li><p><strong>00:00.232</strong>: <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></li>
+<li><p><strong>00:43.395</strong>: <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></li>
+<li><p><strong>00:00.218</strong>: <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></li>
+<li><p><strong>00:00.216</strong>: <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></li>
+<li><p><strong>00:00.216</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
+<li><p><strong>00:00.210</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
</ul>
</div>
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 4305d7d..8f2d444 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 42.27/42.27 result: MeasureResult(costs=(0.0054765041578947364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6218910217285156, timestamp=1648221606.4856763) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 6 GFLOPS: 94.35/94.35 result: MeasureResult(costs=(0.002453696416666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7631030082702637, timestamp=1648223399.4223347) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/94.35 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
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/42.27 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/94.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f49d5fcafa2
+ 12: 0x00007f2fbd65dfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 144.64/144.64 result: MeasureResult(costs=(0.0016004863800000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4456572532653809, timestamp=1648221633.0995505) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 143.12/143.12 result: MeasureResult(costs=(0.0016175155555555557,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1329972743988037, timestamp=1648223425.5728607) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.002029
+Time cost of this operator: 0.002034
</pre></div>
</div>
<div class="sphx-glr-footer class 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 c52de40..4f997ac 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -553,10 +553,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.2 98.752 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.96 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.288 (1, 1, 10, 10, 3) 1 1
-Total_time - 320.196 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.9 98.658 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.178 0.993 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.12 0.35 (1, 1, 10, 10, 3) 1 1
+Total_time - 320.198 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 190.2 98.511 (1, 1, 10, 10, 6) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.948 1.009 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.927 0.48 (1, 3, 10, 10, 1) 1 1
-Total_time - 193.075 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 217.2 98.68 (1, 1, 10, 10, 6) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.961 0.891 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.945 0.429 (1, 3, 10, 10, 1) 1 1
+Total_time - 220.106 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class 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/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index ab0c131..f4f9327 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:46.456</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:44.090</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:42.101</strong>: <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></li>
-<li><p><strong>00:03.714</strong>: <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></li>
-<li><p><strong>00:00.216</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
-<li><p><strong>00:00.215</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
-<li><p><strong>00:00.210</strong>: <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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:40.033</strong>: <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></li>
+<li><p><strong>00:03.499</strong>: <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></li>
+<li><p><strong>00:00.188</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:00.186</strong>: <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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:00.183</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
</ul>
</div>
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 12f3a2b..a7d1aea 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<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>00:04.588</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:04.548</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.616</strong>: <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></li>
-<li><p><strong>00:01.735</strong>: <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></li>
-<li><p><strong>00:00.236</strong>: <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></li>
+<li><p><strong>00:02.511</strong>: <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></li>
+<li><p><strong>00:01.830</strong>: <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></li>
+<li><p><strong>00:00.208</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/schedule_primitives.html b/docs/how_to/work_with_schedules/schedule_primitives.html
index a79a825..8ebb748 100644
--- a/docs/how_to/work_with_schedules/schedule_primitives.html
+++ b/docs/how_to/work_with_schedules/schedule_primitives.html
@@ -613,15 +613,15 @@ tensors at the root separately by default.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- A: Buffer(A_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, m) {
- B[(i*stride_2)] = (A[(i*stride_1)] + 1f32)
+ B[(i*stride_2)] = (A[(i*stride)] + 1f32)
}
for (i_1: int32, 0, m) {
- C[(i_1*stride)] = (B[(i_1*stride_2)]*2f32)
+ C[(i_1*stride_1)] = (B[(i_1*stride_2)]*2f32)
}
}
</pre></div>
@@ -640,13 +640,13 @@ of computation of <cite>C</cite>.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- A: Buffer(A_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
B: Buffer(B_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto")}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (i: int32, 0, m) {
- B[(i*stride_2)] = (A[(i*stride_1)] + 1f32)
- C[(i*stride)] = (B[(i*stride_2)]*2f32)
+ B[(i*stride_2)] = (A[(i*stride)] + 1f32)
+ C[(i*stride_1)] = (B[(i*stride_2)]*2f32)
}
}
</pre></div>
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 ab86cb3..c11fae3 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>00:06.329</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.015</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.319</strong>: <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></li>
-<li><p><strong>00:01.313</strong>: <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></li>
-<li><p><strong>00:00.806</strong>: <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></li>
-<li><p><strong>00:00.795</strong>: <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></li>
-<li><p><strong>00:00.346</strong>: <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></li>
-<li><p><strong>00:00.258</strong>: <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></li>
-<li><p><strong>00:00.252</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
-<li><p><strong>00:00.241</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
+<li><p><strong>00:02.235</strong>: <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></li>
+<li><p><strong>00:01.272</strong>: <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></li>
+<li><p><strong>00:00.755</strong>: <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></li>
+<li><p><strong>00:00.754</strong>: <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></li>
+<li><p><strong>00:00.314</strong>: <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></li>
+<li><p><strong>00:00.242</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
+<li><p><strong>00:00.231</strong>: <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></li>
+<li><p><strong>00:00.212</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 88d0596..9316d5b 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -548,8 +548,8 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
A: Buffer(A_2: Pointer(float32), float32, [65536], []),
B: Buffer(B_2: Pointer(float32), float32, [32768], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp8bd7_y5r/input0.cc'
-source_filename = "/tmp/tmp8bd7_y5r/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpthaxxy9l/input0.cc'
+source_filename = "/tmp/tmpthaxxy9l/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
diff --git a/docs/how_to/work_with_schedules/tuple_inputs.html b/docs/how_to/work_with_schedules/tuple_inputs.html
index 3bcbc8b..b27543d 100644
--- a/docs/how_to/work_with_schedules/tuple_inputs.html
+++ b/docs/how_to/work_with_schedules/tuple_inputs.html
@@ -425,17 +425,17 @@ with <code class="xref py py-func docutils literal notranslate"><span class="pre
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(idx_1: handle, val_1: handle, T_2: handle, T_3: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {T: Buffer(T_4: Pointer(int32), int32, [(stride: int32*m: int32)], [], type="auto"),
- T_1: Buffer(T_5: Pointer(int32), int32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {T_1: Buffer(T_4: Pointer(int32), int32, [(stride: int32*m: int32)], [], type="auto"),
+ T: Buffer(T_5: Pointer(int32), int32, [(stride_1: int32*m)], [], type="auto"),
idx: Buffer(idx_2: Pointer(int32), int32, [(stride_2: int32*m)], [], type="auto"),
val: Buffer(val_2: Pointer(int32), int32, [(stride_3: int32*m)], [], type="auto")}
buffer_map = {idx_1: idx, val_1: val, T_2: T, T_3: T_1} {
for (i: int32, 0, m) {
- T[(i*stride)] = -1
- T_1[(i*stride_1)] = -2147483648
+ T[(i*stride_1)] = -1
+ T_1[(i*stride)] = -2147483648
for (k: int32, 0, n: int32) {
- T[(i*stride)] = @tir.if_then_else((val[((i*stride_3) + (k*stride_4: int32))] <= T_1[(i*stride_1)]), T[(i*stride)], idx[((i*stride_2) + (k*stride_5: int32))], dtype=int32)
- T_1[(i*stride_1)] = @tir.if_then_else((val[((i*stride_3) + (k*stride_4))] <= T_1[(i*stride_1)]), T_1[(i*stride_1)], val[((i*stride_3) + (k*stride_4))], dtype=int32)
+ T[(i*stride_1)] = @tir.if_then_else((val[((i*stride_3) + (k*stride_4: int32))] <= T_1[(i*stride)]), T[(i*stride_1)], idx[((i*stride_2) + (k*stride_5: int32))], dtype=int32)
+ T_1[(i*stride)] = @tir.if_then_else((val[((i*stride_3) + (k*stride_4))] <= T_1[(i*stride)]), T_1[(i*stride)], val[((i*stride_3) + (k*stride_4))], dtype=int32)
}
}
}
@@ -468,19 +468,19 @@ in terms of operation.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A0_1: handle, A1_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {A0: Buffer(A0_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
- C: Buffer(C_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [(stride: int32*m: int32)], [], type="auto"),
+ A0: Buffer(A0_2: Pointer(float32), float32, [(stride_1: int32*m)], [], type="auto"),
A1: Buffer(A1_2: Pointer(float32), float32, [(stride_2: int32*m)], [], type="auto")}
buffer_map = {A0_1: A0, A1_1: A1, C_1: C} {
allocate(B.v0: Pointer(global float32), float32, [n: int32]), storage_scope = global;
allocate(B.v1: Pointer(global float32), float32, [n]), storage_scope = global;
for (i: int32, 0, m) {
for (j: int32, 0, n) {
- B.v0_1: Buffer(B.v0, float32, [n], [])[j] = (A0[((i*stride) + (j*stride_3: int32))] + 2f32)
- B.v1_1: Buffer(B.v1, float32, [n], [])[j] = (A0[((i*stride) + (j*stride_3))]*3f32)
+ B.v0_1: Buffer(B.v0, float32, [n], [])[j] = (A0[((i*stride_1) + (j*stride_3: int32))] + 2f32)
+ B.v1_1: Buffer(B.v1, float32, [n], [])[j] = (A0[((i*stride_1) + (j*stride_3))]*3f32)
}
for (j_1: int32, 0, n) {
- C[((i*stride_1) + (j_1*stride_4: int32))] = (A1[((i*stride_2) + (j_1*stride_5: int32))] + B.v0_1[j_1])
+ C[((i*stride) + (j_1*stride_4: int32))] = (A1[((i*stride_2) + (j_1*stride_5: int32))] + B.v0_1[j_1])
}
}
}
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 51a2de1..fb5dc9d 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1713,7 +1713,7 @@ Can be the a function or the function name.</p></li>
<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">
@@ -1750,7 +1750,7 @@ the initial naive schedule (state).</p>
<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>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index b41d742..9d467a3 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/532b2b4a6/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 42350bf..a5be1ab 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/532b2b4a6/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 2331cb6..c868636 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/532b2b4a6/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 bcac28d..c2ccf7d 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/532b2b4a6/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 4cce9c4..a2e057a 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/532b2b4a6/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 7241ab3..a8420d0 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/532b2b4a6/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 ff82f41..38480ca 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/532b2b4a6/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 25e2845..0864c9b 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/532b2b4a6/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/web/src/runtime.ts#L1134">runtime.ts:1134</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/532b2b4a6/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 48e5af3..d0ff3fc 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/532b2b4a6/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 208d569..0969a23 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/532b2b4a6/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 241e6e8..5df17a6 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/532b2b4a6/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 0c30fa4..9d1c6f1 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/532b2b4a6/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 673d590..4ade8bd 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/532b2b4a6/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 5852b22..150edb3 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/532b2b4a6/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 79ab5a2..cc49f2f 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/532b2b4a6/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 628670b..107b198 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/532b2b4a6/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 c8d6eb1..9dc09c3 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/532b2b4a6/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 843248b..93f12bb 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/532b2b4a6/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 649daf9..c982377 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/532b2b4a6/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 00e010d..5a63d0f 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/532b2b4a6/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 f87f46d..2449781 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/532b2b4a6/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/web/src/runtime.ts#L1356">runtime.ts:1356</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/532b2b4a6/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 fe449a7..3702b23 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/532b2b4a6/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 5afb8e0..67d6edb 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/532b2b4a6/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 dec5597..ed3f60e 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/532b2b4a6/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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/532b2b4a6/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/14084f4c3/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 84526b6..8c19853 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 ebd641e..1169866 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.900</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:19.635</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:20.677</strong>: <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></li>
-<li><p><strong>00:00.223</strong>: <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></li>
+<li><p><strong>00:19.435</strong>: <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></li>
+<li><p><strong>00:00.200</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index ca77d74..1e75e97 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -539,7 +539,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.36s!
+resnet18_v1 inference graph built in 20.49s!
</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 aaf8573..f591f9b 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -557,7 +557,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.22s!
+yolov3-tiny inference graph built in 14.22s!
</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 b2a6ce3..291e9a1 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>01:29.572</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:25.742</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:47.149</strong>: <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></li>
-<li><p><strong>00:42.423</strong>: <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></li>
+<li><p><strong>00:45.509</strong>: <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></li>
+<li><p><strong>00:40.233</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/optimize/convolution_opt.html b/docs/topic/vta/tutorials/optimize/convolution_opt.html
index 1f9cbbe..5804579 100644
--- a/docs/topic/vta/tutorials/optimize/convolution_opt.html
+++ b/docs/topic/vta/tutorials/optimize/convolution_opt.html
@@ -525,8 +525,8 @@ Those include:</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(data_1: handle, kernel_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {data: Buffer(data_2: Pointer(int8), int8, [50176], []),
- res: Buffer(res_2: Pointer(int8), int8, [50176], []),
+ buffers = {res: Buffer(res_2: Pointer(int8), int8, [50176], []),
+ data: Buffer(data_2: Pointer(int8), int8, [50176], []),
kernel: Buffer(kernel_2: Pointer(int8), int8, [589824], [])}
buffer_map = {data_1: data, kernel_1: kernel, res_1: res} {
allocate(data_buf: Pointer(global int8), int8, [65536]), storage_scope = global;
@@ -697,8 +697,8 @@ below.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(data_1: handle, kernel_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {res: Buffer(res_2: Pointer(int8), int8, [50176], []),
- data: Buffer(data_2: Pointer(int8), int8, [50176], []),
+ buffers = {data: Buffer(data_2: Pointer(int8), int8, [50176], []),
+ res: Buffer(res_2: Pointer(int8), int8, [50176], []),
kernel: Buffer(kernel_2: Pointer(int8), int8, [589824], [])}
buffer_map = {data_1: data, kernel_1: kernel, res_1: res} {
allocate(data_buf: Pointer(global int8), int8, [65536]), storage_scope = global;
@@ -883,8 +883,8 @@ and mapping the shift, and clipping computation to the vector ALU.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(data_1: handle, kernel_1: handle, res_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {data: Buffer(data_2: Pointer(int8), int8, [50176], []),
- res: Buffer(res_2: Pointer(int8), int8, [50176], []),
+ buffers = {res: Buffer(res_2: Pointer(int8), int8, [50176], []),
+ data: Buffer(data_2: Pointer(int8), int8, [50176], []),
kernel: Buffer(kernel_2: Pointer(int8), int8, [589824], [])}
buffer_map = {data_1: data, kernel_1: kernel, res_1: res} {
@tir.vta.coproc_dep_push(3, 2, dtype=int32)
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 9575340..1256ba4 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:03.648</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.553</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:03.039</strong>: <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></li>
-<li><p><strong>00:00.609</strong>: <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></li>
+<li><p><strong>00:02.989</strong>: <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></li>
+<li><p><strong>00:00.564</strong>: <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></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 1e4bc55..6a5d4d8 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -300,10 +300,10 @@
<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>00:01.107</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:01.036</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:00.554</strong>: <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></li>
-<li><p><strong>00:00.553</strong>: <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></li>
+<li><p><strong>00:00.524</strong>: <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></li>
+<li><p><strong>00:00.511</strong>: <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></li>
</ul>
</div>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 1388521..c91e049 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -453,7 +453,7 @@ trials, we can load the best schedule from the log file and apply it.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
</pre></div>
</div>
</div>
@@ -472,8 +472,8 @@ operator fusion.</p>
@main = primfn(A_1: handle, B_1: handle, C_1: handle, out_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {out: Buffer(out_2: Pointer(float32), float32, [1048576], []),
- C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C, out_1: out} {
allocate(auto_scheduler_layout_transform: Pointer(global float32), float32, [1048576]), storage_scope = global {
@@ -544,7 +544,7 @@ operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.515 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.852 ms
</pre></div>
</div>
</div>
@@ -620,6 +620,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.937 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download 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_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 0d6b0eb..d1fdcb5 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -513,7 +513,7 @@ standard deviation.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 498.4630057199991, 'median': 498.29967405000275, 'std': 0.5841999958077553}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 491.0830640700011, 'median': 491.01350355000477, 'std': 0.4615301791043869}
</pre></div>
</div>
</div>
@@ -667,128 +667,129 @@ depending on the specifics of the model and the target platform.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 1/25] Current/Best: 17.83/ 21.13 GFLOPS | Progress: (4/10) | 5.10 s
-[Task 1/25] Current/Best: 14.30/ 23.49 GFLOPS | Progress: (8/10) | 8.20 s
-[Task 1/25] Current/Best: 12.96/ 23.49 GFLOPS | Progress: (10/10) | 9.05 s Done.
+[Task 1/25] Current/Best: 8.81/ 14.27 GFLOPS | Progress: (4/10) | 5.95 s
+[Task 1/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (8/10) | 8.36 s
+[Task 1/25] Current/Best: 1.93/ 21.22 GFLOPS | Progress: (10/10) | 10.48 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 2/25] Current/Best: 8.73/ 16.70 GFLOPS | Progress: (4/10) | 2.80 s
-[Task 2/25] Current/Best: 17.97/ 17.97 GFLOPS | Progress: (8/10) | 4.65 s
-[Task 2/25] Current/Best: 14.58/ 17.97 GFLOPS | Progress: (10/10) | 5.22 s Done.
+[Task 2/25] Current/Best: 11.98/ 16.80 GFLOPS | Progress: (4/10) | 3.65 s
+[Task 2/25] Current/Best: 17.29/ 19.90 GFLOPS | Progress: (8/10) | 4.90 s
+[Task 2/25] Current/Best: 20.16/ 20.16 GFLOPS | Progress: (10/10) | 5.58 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 3/25] Current/Best: 6.27/ 17.55 GFLOPS | Progress: (4/10) | 3.50 s
-[Task 3/25] Current/Best: 20.75/ 20.75 GFLOPS | Progress: (8/10) | 5.32 s
-[Task 3/25] Current/Best: 13.53/ 20.75 GFLOPS | Progress: (10/10) | 6.87 s Done.
+[Task 3/25] Current/Best: 9.88/ 16.60 GFLOPS | Progress: (4/10) | 3.74 s
+[Task 3/25] Current/Best: 12.70/ 16.60 GFLOPS | Progress: (8/10) | 6.47 s
+[Task 3/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (10/10) | 7.35 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 4/25] Current/Best: 6.63/ 16.08 GFLOPS | Progress: (4/10) | 2.77 s
-[Task 4/25] Current/Best: 13.61/ 16.08 GFLOPS | Progress: (8/10) | 6.94 s
-[Task 4/25] Current/Best: 12.49/ 16.08 GFLOPS | Progress: (10/10) | 7.93 s Done.
+[Task 4/25] Current/Best: 11.83/ 11.83 GFLOPS | Progress: (4/10) | 5.50 s
+[Task 4/25] Current/Best: 3.87/ 16.77 GFLOPS | Progress: (8/10) | 8.51 s
+[Task 4/25] Current/Best: 15.41/ 16.77 GFLOPS | Progress: (10/10) | 9.59 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 5/25] Current/Best: 5.68/ 22.60 GFLOPS | Progress: (4/10) | 2.56 s
-[Task 5/25] Current/Best: 22.45/ 22.60 GFLOPS | Progress: (8/10) | 4.10 s
-[Task 5/25] Current/Best: 18.58/ 22.60 GFLOPS | Progress: (10/10) | 4.92 s Done.
+[Task 5/25] Current/Best: 14.84/ 20.41 GFLOPS | Progress: (4/10) | 3.82 s
+[Task 5/25] Current/Best: 3.50/ 20.41 GFLOPS | Progress: (8/10) | 6.11 s
+[Task 5/25] Current/Best: 1.71/ 20.41 GFLOPS | Progress: (10/10) | 7.43 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 6/25] Current/Best: 4.72/ 17.15 GFLOPS | Progress: (4/10) | 3.67 s
-[Task 6/25] Current/Best: 8.84/ 17.15 GFLOPS | Progress: (8/10) | 6.38 s
-[Task 6/25] Current/Best: 7.13/ 17.15 GFLOPS | Progress: (10/10) | 8.12 s Done.
+[Task 6/25] Current/Best: 9.02/ 23.30 GFLOPS | Progress: (4/10) | 2.64 s
+[Task 6/25] Current/Best: 13.18/ 23.30 GFLOPS | Progress: (8/10) | 5.39 s
+[Task 6/25] Current/Best: 18.44/ 23.30 GFLOPS | Progress: (10/10) | 6.42 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 7/25] Current/Best: 1.60/ 17.24 GFLOPS | Progress: (4/10) | 4.38 s
-[Task 7/25] Current/Best: 14.76/ 23.20 GFLOPS | Progress: (8/10) | 6.01 s
-[Task 7/25] Current/Best: 8.49/ 23.20 GFLOPS | Progress: (10/10) | 7.05 s Done.
+[Task 7/25] Current/Best: 13.90/ 22.33 GFLOPS | Progress: (4/10) | 2.62 s
+[Task 7/25] Current/Best: 14.69/ 22.38 GFLOPS | Progress: (8/10) | 4.55 s
+[Task 7/25] Current/Best: 9.90/ 22.38 GFLOPS | Progress: (10/10) | 6.98 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 8/25] Current/Best: 17.45/ 18.06 GFLOPS | Progress: (4/10) | 2.71 s
-[Task 8/25] Current/Best: 17.69/ 18.06 GFLOPS | Progress: (8/10) | 9.09 s
-[Task 8/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (10/10) | 10.42 s Done.
+[Task 8/25] Current/Best: 15.29/ 15.91 GFLOPS | Progress: (4/10) | 12.26 s
+[Task 8/25] Current/Best: 16.59/ 19.47 GFLOPS | Progress: (8/10) | 14.43 s
+[Task 8/25] Current/Best: 22.12/ 22.12 GFLOPS | Progress: (10/10) | 15.97 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 9/25] Current/Best: 12.03/ 18.02 GFLOPS | Progress: (4/10) | 7.68 s
-[Task 9/25] Current/Best: 12.00/ 18.02 GFLOPS | Progress: (8/10) | 18.43 s
-[Task 9/25] Current/Best: 22.69/ 22.69 GFLOPS | Progress: (10/10) | 19.40 s Done.
-
+[Task 9/25] Current/Best: 21.77/ 21.77 GFLOPS | Progress: (4/10) | 20.72 s
+[Task 9/25] Current/Best: 17.27/ 21.77 GFLOPS | Progress: (8/10) | 22.61 s
+[Task 9/25] Current/Best: 16.13/ 21.77 GFLOPS | Progress: (10/10) | 26.89 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 10/25] Current/Best: 10.44/ 18.27 GFLOPS | Progress: (4/10) | 3.83 s
-[Task 10/25] Current/Best: 13.82/ 18.27 GFLOPS | Progress: (8/10) | 5.33 s
-[Task 10/25] Current/Best: 13.72/ 18.27 GFLOPS | Progress: (10/10) | 6.43 s Done.
+[Task 10/25] Current/Best: 16.03/ 16.03 GFLOPS | Progress: (4/10) | 2.32 s
+[Task 10/25] Current/Best: 4.95/ 22.79 GFLOPS | Progress: (8/10) | 4.13 s
+[Task 10/25] Current/Best: 4.17/ 22.79 GFLOPS | Progress: (10/10) | 5.10 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 11/25] Current/Best: 9.01/ 23.56 GFLOPS | Progress: (4/10) | 3.04 s
-[Task 11/25] Current/Best: 12.15/ 23.56 GFLOPS | Progress: (8/10) | 5.23 s
-[Task 11/25] Current/Best: 15.20/ 23.56 GFLOPS | Progress: (10/10) | 6.22 s Done.
+[Task 11/25] Current/Best: 17.24/ 23.42 GFLOPS | Progress: (4/10) | 2.87 s
+[Task 11/25] Current/Best: 15.91/ 23.62 GFLOPS | Progress: (8/10) | 5.01 s
+[Task 11/25] Current/Best: 19.37/ 23.62 GFLOPS | Progress: (10/10) | 5.86 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 12/25] Current/Best: 13.71/ 15.70 GFLOPS | Progress: (4/10) | 3.89 s
-[Task 12/25] Current/Best: 10.05/ 15.70 GFLOPS | Progress: (8/10) | 6.24 s
-[Task 12/25] Current/Best: 6.51/ 15.70 GFLOPS | Progress: (10/10) | 7.46 s Done.
+[Task 12/25] Current/Best: 6.28/ 15.64 GFLOPS | Progress: (4/10) | 9.37 s
+[Task 12/25] Current/Best: 6.38/ 17.64 GFLOPS | Progress: (8/10) | 12.23 s
+[Task 12/25] Current/Best: 4.86/ 17.64 GFLOPS | Progress: (10/10) | 13.44 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 13/25] Current/Best: 15.74/ 16.83 GFLOPS | Progress: (4/10) | 3.07 s
-[Task 13/25] Current/Best: 14.34/ 18.01 GFLOPS | Progress: (8/10) | 5.65 s
-[Task 13/25] Current/Best: 22.20/ 22.20 GFLOPS | Progress: (10/10) | 6.69 s Done.
+[Task 13/25] Current/Best: 14.96/ 23.18 GFLOPS | Progress: (4/10) | 2.96 s
+[Task 13/25] Current/Best: 9.35/ 23.18 GFLOPS | Progress: (8/10) | 6.13 s
+[Task 13/25] Current/Best: 9.10/ 23.18 GFLOPS | Progress: (10/10) | 7.76 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 14/25] Current/Best: 19.38/ 19.39 GFLOPS | Progress: (4/10) | 2.78 s
-[Task 14/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (8/10) | 6.63 s
-[Task 14/25] Current/Best: 21.42/ 21.42 GFLOPS | Progress: (10/10) | 7.45 s Done.
-
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 15/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (4/10) | 2.37 s
-[Task 15/25] Current/Best: 11.79/ 21.91 GFLOPS | Progress: (8/10) | 4.89 s
-[Task 15/25] Current/Best: 20.77/ 21.91 GFLOPS | Progress: (10/10) | 5.44 s Done.
-
+[Task 14/25] Current/Best: 9.06/ 18.71 GFLOPS | Progress: (4/10) | 6.12 s
+[Task 14/25] Current/Best: 10.61/ 18.71 GFLOPS | Progress: (8/10) | 8.61 s
+[Task 14/25] Current/Best: 12.55/ 18.71 GFLOPS | Progress: (10/10) | 9.84 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+ Done.
+
+[Task 15/25] Current/Best: 7.61/ 23.93 GFLOPS | Progress: (4/10) | 3.76 s
+[Task 15/25] Current/Best: 15.21/ 23.93 GFLOPS | Progress: (8/10) | 5.14 s
+[Task 15/25] Current/Best: 18.45/ 23.93 GFLOPS | Progress: (10/10) | 5.84 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 16/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (4/10) | 2.90 s
-[Task 16/25] Current/Best: 7.54/ 21.17 GFLOPS | Progress: (8/10) | 5.81 s
-[Task 16/25] Current/Best: 11.19/ 21.17 GFLOPS | Progress: (10/10) | 6.39 s Done.
+[Task 16/25] Current/Best: 15.70/ 19.16 GFLOPS | Progress: (4/10) | 2.62 s
+[Task 16/25] Current/Best: 9.95/ 19.16 GFLOPS | Progress: (8/10) | 5.91 s
+[Task 16/25] Current/Best: 16.27/ 19.16 GFLOPS | Progress: (10/10) | 6.88 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 17/25] Current/Best: 1.56/ 15.57 GFLOPS | Progress: (4/10) | 4.54 s
-[Task 17/25] Current/Best: 16.38/ 23.08 GFLOPS | Progress: (8/10) | 6.95 s
-[Task 17/25] Current/Best: 19.49/ 23.08 GFLOPS | Progress: (10/10) | 7.70 s Done.
+[Task 17/25] Current/Best: 18.39/ 18.39 GFLOPS | Progress: (4/10) | 2.56 s
+[Task 17/25] Current/Best: 1.56/ 18.58 GFLOPS | Progress: (8/10) | 6.28 s
+[Task 17/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (10/10) | 6.96 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 18/25] Current/Best: 10.45/ 10.45 GFLOPS | Progress: (4/10) | 7.87 s
-[Task 18/25] Current/Best: 22.26/ 22.26 GFLOPS | Progress: (8/10) | 9.58 s
-[Task 18/25] Current/Best: 9.87/ 22.26 GFLOPS | Progress: (10/10) | 12.35 s Done.
+[Task 18/25] Current/Best: 6.50/ 16.25 GFLOPS | Progress: (4/10) | 4.49 s
+[Task 18/25] Current/Best: 16.04/ 18.48 GFLOPS | Progress: (8/10) | 6.05 s
+[Task 18/25] Current/Best: 9.56/ 18.48 GFLOPS | Progress: (10/10) | 7.59 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 19/25] Current/Best: 17.64/ 18.73 GFLOPS | Progress: (4/10) | 4.67 s
-[Task 19/25] Current/Best: 12.05/ 21.18 GFLOPS | Progress: (8/10) | 9.43 s
-[Task 19/25] Current/Best: 6.16/ 21.18 GFLOPS | Progress: (10/10) | 10.70 s Done.
+[Task 19/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (4/10) | 2.94 s
+[Task 19/25] Current/Best: 10.85/ 22.60 GFLOPS | Progress: (8/10) | 7.92 s
+[Task 19/25] Current/Best: 15.98/ 22.60 GFLOPS | Progress: (10/10) | 8.82 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 20/25] Current/Best: 6.91/ 17.61 GFLOPS | Progress: (4/10) | 3.37 s
-[Task 20/25] Current/Best: 16.91/ 17.61 GFLOPS | Progress: (8/10) | 5.88 s
-[Task 20/25] Current/Best: 16.88/ 17.61 GFLOPS | Progress: (10/10) | 6.74 s
+[Task 20/25] Current/Best: 7.22/ 13.42 GFLOPS | Progress: (4/10) | 4.39 s
+[Task 20/25] Current/Best: 2.51/ 17.11 GFLOPS | Progress: (8/10) | 6.61 s
+[Task 20/25] Current/Best: 1.57/ 17.11 GFLOPS | Progress: (10/10) | 8.96 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 21/25] Current/Best: 10.97/ 10.97 GFLOPS | Progress: (4/10) | 3.74 s Done.
+[Task 21/25] Current/Best: 13.79/ 20.24 GFLOPS | Progress: (4/10) | 2.60 s
+[Task 21/25] Current/Best: 17.16/ 20.24 GFLOPS | Progress: (8/10) | 4.12 s
+[Task 21/25] Current/Best: 12.08/ 20.24 GFLOPS | Progress: (10/10) | 5.26 s
+[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+ Done.
+ Done.
-[Task 21/25] Current/Best: 4.74/ 22.36 GFLOPS | Progress: (8/10) | 5.70 s
-[Task 21/25] Current/Best: 16.04/ 22.36 GFLOPS | Progress: (10/10) | 6.39 s Done.
-
-[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 22/25] Current/Best: 6.79/ 18.99 GFLOPS | Progress: (4/10) | 3.42 s
-[Task 22/25] Current/Best: 2.69/ 18.99 GFLOPS | Progress: (8/10) | 5.90 s
-[Task 22/25] Current/Best: 9.62/ 18.99 GFLOPS | Progress: (10/10) | 7.76 s Done.
+[Task 22/25] Current/Best: 5.93/ 19.33 GFLOPS | Progress: (4/10) | 3.80 s
+[Task 22/25] Current/Best: 9.71/ 19.33 GFLOPS | Progress: (8/10) | 6.20 s
+[Task 22/25] Current/Best: 16.48/ 19.33 GFLOPS | Progress: (10/10) | 6.79 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 23/25] Current/Best: 17.95/ 20.98 GFLOPS | Progress: (4/10) | 3.41 s
-[Task 23/25] Current/Best: 14.30/ 20.98 GFLOPS | Progress: (8/10) | 5.62 s
-[Task 23/25] Current/Best: 15.34/ 20.98 GFLOPS | Progress: (10/10) | 6.56 s Done.
+[Task 23/25] Current/Best: 16.20/ 20.92 GFLOPS | Progress: (4/10) | 3.67 s
+[Task 23/25] Current/Best: 11.53/ 21.75 GFLOPS | Progress: (8/10) | 5.79 s
+[Task 23/25] Current/Best: 17.66/ 21.75 GFLOPS | Progress: (10/10) | 7.09 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 24/25] Current/Best: 7.29/ 7.29 GFLOPS | Progress: (4/10) | 4.31 s
-[Task 24/25] Current/Best: 2.51/ 7.29 GFLOPS | Progress: (8/10) | 18.77 s
-[Task 24/25] Current/Best: 3.56/ 7.29 GFLOPS | Progress: (10/10) | 21.60 s
+[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (4/10) | 88.02 s
+[Task 24/25] Current/Best: 3.96/ 3.96 GFLOPS | Progress: (8/10) | 101.96 s
+[Task 24/25] Current/Best: 1.56/ 3.96 GFLOPS | Progress: (10/10) | 113.65 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 25/25] Current/Best: 4.84/ 9.54 GFLOPS | Progress: (4/10) | 4.58 s
-[Task 25/25] Current/Best: 5.73/ 9.54 GFLOPS | Progress: (8/10) | 5.94 s
-[Task 25/25] Current/Best: 3.03/ 9.54 GFLOPS | Progress: (10/10) | 6.45 s Done.
+[Task 25/25] Current/Best: 6.59/ 8.43 GFLOPS | Progress: (4/10) | 5.82 s Done.
+
+[Task 25/25] Current/Best: 8.82/ 8.82 GFLOPS | Progress: (8/10) | 6.97 s
+[Task 25/25] Current/Best: 7.60/ 8.82 GFLOPS | Progress: (10/10) | 7.48 s Done.
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -851,7 +852,7 @@ model using optimized operators to speed up our computations.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356379
+class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -889,8 +890,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 430.49108314999904, 'median': 430.111272649998, 'std': 0.9557213800757237}
-unoptimized: {'mean': 498.4630057199991, 'median': 498.29967405000275, 'std': 0.5841999958077553}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 437.42848505999973, 'median': 437.4217916500015, 'std': 0.7323361024402074}
+unoptimized: {'mean': 491.0830640700011, 'median': 491.01350355000477, 'std': 0.4615301791043869}
</pre></div>
</div>
</div>
@@ -904,7 +905,7 @@ 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> ( 6 minutes 43.192 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 8 minutes 30.565 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download 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 c5e204f..4b24fb6 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -496,7 +496,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.26e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.288e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index ac045a4..52f946e 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -458,7 +458,7 @@ we can schedule the following series of operations ending with <code class="code
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x193f69d0)), stage(b, placeholder(b, 0x19bc37c0)), 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, 0x1985d970)), stage(b, placeholder(b, 0x43dc560)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index c266f34..3debaad 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -300,20 +300,20 @@
<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>09:24.662</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>11:36.363</strong> total execution time for <strong>tutorial</strong> files:</p>
<ul class="simple">
-<li><p><strong>06:43.192</strong>: <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></li>
-<li><p><strong>00:59.552</strong>: <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></li>
-<li><p><strong>00:59.163</strong>: <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></li>
-<li><p><strong>00:26.648</strong>: <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></li>
-<li><p><strong>00:13.760</strong>: <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></li>
-<li><p><strong>00:01.190</strong>: <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></li>
-<li><p><strong>00:00.730</strong>: <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></li>
-<li><p><strong>00:00.222</strong>: <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></li>
-<li><p><strong>00:00.053</strong>: <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></li>
-<li><p><strong>00:00.053</strong>: <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></li>
-<li><p><strong>00:00.050</strong>: <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></li>
-<li><p><strong>00:00.048</strong>: <a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></li>
+<li><p><strong>08:30.565</strong>: <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></li>
+<li><p><strong>01:14.937</strong>: <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></li>
+<li><p><strong>01:02.135</strong>: <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></li>
+<li><p><strong>00:25.939</strong>: <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></li>
+<li><p><strong>00:20.680</strong>: <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></li>
+<li><p><strong>00:01.090</strong>: <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></li>
+<li><p><strong>00:00.693</strong>: <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></li>
+<li><p><strong>00:00.200</strong>: <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></li>
+<li><p><strong>00:00.037</strong>: <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></li>
+<li><p><strong>00:00.030</strong>: <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></li>
+<li><p><strong>00:00.030</strong>: <a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></li>
+<li><p><strong>00:00.029</strong>: <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></li>
</ul>
</div>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 4c0b497..c79ac9e 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -558,7 +558,7 @@ compile and run this new schedule with the parallel operation applied:</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000006
</pre></div>
</div>
</div>
@@ -631,10 +631,10 @@ factor to be the number of threads on your CPU.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.68407999998999e-06 1.0
- naive 5.856e-06 0.7620951369594836
-parallel 6.9837000000000006e-06 0.908853109286876
- vector 2.4532300000000002e-05 3.192613819745755
+ numpy 8.134429999699932e-06 1.0
+ naive 5.8989e-06 0.7251768102027558
+parallel 6.0761999999999995e-06 0.7469730516119928
+ vector 2.45311e-05 3.0157122257988473
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -952,7 +952,7 @@ matrix multiplication.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019290
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017880
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -994,7 +994,7 @@ optimizations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.258723
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.510692
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1060,7 +1060,7 @@ schedule.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.329134
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.306112
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1072,8 +1072,8 @@ internal representation and compare it to the original:</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x.outer: int32, 0, 32) {
@@ -1120,11 +1120,11 @@ already cache friendly from our previous optimizations.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.349938
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.339071
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
- buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
- A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
+ C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (x.outer: int32, 0, 32) {
@@ -1175,7 +1175,7 @@ more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.121660
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.114924
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1251,7 +1251,7 @@ optimized schedule.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108962
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109074
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1325,11 +1325,11 @@ to `C</cite> when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110613
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110414
@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], []),
- C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
+ A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
B: Buffer(B_2: Pointer(float32), float32, [1048576], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
allocate(packedB: Pointer(global float32x32), float32x32, [32768]), storage_scope = global;
@@ -1392,7 +1392,7 @@ of thread-level parallelization.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.144784
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.144231
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(float32), float32, [1048576], []),
@@ -1454,13 +1454,13 @@ working, we can compare the results.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.2587225122 1.0
- blocking 0.3291344043 0.10100105273394319
- vectorization 0.3499376062 0.10738490463361153
-loop permutation 0.12165952850000002 0.037333503556848203
- array packing 0.1089624357 0.033437162965569055
- block caching 0.11061333660000001 0.03394377280848124
- parallelization 0.144783868 0.04442963997638903
+ none 3.5106921898000003 1.0
+ blocking 0.3061121634 0.0871942474163304
+ vectorization 0.3390714418 0.09658250381082725
+loop permutation 0.11492392359999999 0.03273540298802074
+ array packing 0.10907418399999999 0.031069139105075975
+ block caching 0.11041368359999999 0.03145068767942601
+ parallelization 0.1442312776 0.041083430218989574
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1492,6 +1492,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.135 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download 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>