You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/01/04 00:27:32 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@45a8a44b862a8653a9a20f94dcd924ad968c9595)
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 e05adb10bb deploying docs (apache/tvm@45a8a44b862a8653a9a20f94dcd924ad968c9595)
e05adb10bb is described below
commit e05adb10bb11f103080284a75bea9d14299fc234
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Jan 4 00:27:25 2023 +0000
deploying docs (apache/tvm@45a8a44b862a8653a9a20f94dcd924ad968c9595)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 335230 -> 315482 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23974 -> 24112 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 7 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 560 +++++----------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 86 +++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 322 ++++++++++--
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 57 +--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 46 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 13 +-
docs/how_to/compile_models/from_pytorch.html | 8 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 3 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 33 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 556 +++++---------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 86 +++-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 322 ++++++++++--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
.../reference/api/doxygen/ir_2attrs_8h_source.html | 2 +-
.../api/doxygen/packed__func_8h_source.html | 14 +-
.../api/doxygen/runtime_2module_8h_source.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++---
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 272 +++++-----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
131 files changed, 1775 insertions(+), 1790 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 4730ebaecb..3ef8e6db47 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 4f63c99e35..663dc220a5 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 6636a08648..ad2f97a58a 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.145 seconds)
+ **Total running time of the script:** ( 1 minutes 11.326 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index ea5c9e5cf5..aa96700cf3 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip0e64d359-98b4-4749-ab70-1d130b09aff1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip9928348d-f117-4a1a-959d-7d8c9e117ef4 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index d89448cdfe..6061197a62 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 43.4MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 46.7MB/s]
45%|####5 | 18.8M/41.5M [00:00<00:00, 41.1MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 42.6MB/s]
80%|######## | 33.3M/41.5M [00:00<00:00, 58.3MB/s]
94%|#########4| 39.2M/41.5M [00:00<00:00, 45.8MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 45.0MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 51.7MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 56.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 58.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 65.5MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 63.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 63.3MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index fa9d44b25d..dc60b0f448 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
27%|##7 | 12.3M/44.7M [00:00<00:00, 129MB/s]
55%|#####4 | 24.6M/44.7M [00:00<00:00, 109MB/s]
79%|#######8 | 35.2M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
31%|### | 13.8M/44.7M [00:00<00:00, 144MB/s]
62%|######1 | 27.5M/44.7M [00:00<00:00, 110MB/s]
86%|########6 | 38.5M/44.7M [00:00<00:00, 81.5MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 96.6MB/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 342ba229d5..53aa41faa2 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.144 seconds)
+ **Total running time of the script:** ( 1 minutes 15.391 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 8ef0409506..8cbcb6b4d0 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:47.707** total execution time for **how_to_compile_models** files:
+**05:55.977** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:13.144 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:15.391 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.145 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.326 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.172 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:49.560 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.042 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.223 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.305 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.727 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.788 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.609 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.394 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.919 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.499 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.169 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.771 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.580 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.446 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.473 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index ea39adeb83..da6800d014 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,18 +723,13 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 3342.0276 3342.0027 3347.9278 3338.6830 2.7855
+ 2689.6413 2689.0762 2692.5543 2687.0643 1.9732
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.436 seconds)
-
-
.. _sphx_glr_download_how_to_deploy_models_deploy_model_on_adreno.py:
.. only:: html
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 3c1ada365c..0831603769 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
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1540 16.1293 16.4871 15.9801 0.1393
+ 17.1583 17.2891 17.5560 16.5525 0.3264
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 56f1b5067f..cef2692fb8 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
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 8.12M/170M [00:00<00:02, 79.1MB/s]
9%|9 | 15.7M/170M [00:00<00:02, 60.6MB/s]
24%|##3 | 40.0M/170M [00:00<00:01, 132MB/s]
32%|###1 | 53.8M/170M [00:00<00:00, 136MB/s]
40%|###9 | 67.5M/170M [00:00<00:00, 121MB/s]
47%|####6 | 79.7M/170M [00:00<00:00, 114MB/s]
54%|#####3 | 91.0M/170M [00:00<00:00, 105MB/s]
60%|###### | 102M/170M [00:00<00:00, 108MB/s]
66%|######6 | 113M/170M [00:01<00:00, 102MB/s]
72%|#######2 | 123M/170M [00:01<00:00, 98.2MB/s]
78%|#######7 | 132M/170M [00:01<00:00, 89.5MB/s]
83%|########2 | 141M/170M [00:01<00:00, 87.9MB/s]
88%|########7 | 149M/170M [00:01<00:00, 67.0MB/s]
93%|#########3| 158M/170M [00:01<00:00, 68.4MB/s]
99%|#########8| 168M/170M [00:01<00:00, 74.5MB/s]
100%|##########| 170M/170M [00:01<00:00, 92.4MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|9 | 16.0M/170M [00:00<00:00, 164MB/s]
19%|#8 | 31.6M/170M [00:00<00:01, 118MB/s]
26%|##5 | 43.6M/170M [00:00<00:01, 114MB/s]
32%|###2 | 54.8M/170M [00:00<00:01, 108MB/s]
38%|###8 | 65.2M/170M [00:00<00:01, 98.9MB/s]
45%|####5 | 76.9M/170M [00:00<00:00, 106MB/s]
51%|#####1 | 87.1M/170M [00:00<00:00, 104MB/s]
57%|#####7 | 97.2M/170M [00:01<00:00, 83.4MB/s]
64%|######4 | 109M/170M [00:01<00:00, 92.9MB/s]
73%|#######3 | 124M/170M [00:01<00:00, 111MB/s]
80%|#######9 | 135M/170M [00:01<00:00, 107MB/s]
86%|########6 | 146M/170M [00:01<00:00, 102MB/s]
92%|#########2| 157M/170M [00:01<00:00, 104MB/s]
98%|#########8| 167M/170M [00:01<00:00, 103MB/s]
100%|##########| 170M/170M [00:01<00:00, 103MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 19.158 seconds)
+ **Total running time of the script:** ( 3 minutes 27.841 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 3337640abc..c3f3a885bc 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 41.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 58.7MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 82.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 96.4MB/s]
@@ -418,7 +418,7 @@ 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)
- 90.4580 90.4380 90.9870 90.0762 0.1651
+ 90.5616 90.5090 92.7981 90.1705 0.3468
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.901 seconds)
+ **Total running time of the script:** ( 1 minutes 9.196 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 9e9866fcc1..eeb7ad1e6e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.4326 121.4678 123.0171 120.2928 0.5353
+ 121.0469 120.9888 122.4999 120.1383 0.4405
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 32.309 seconds)
+ **Total running time of the script:** ( 2 minutes 29.987 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 ef128965ef..82a7aa4509 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 27.141 seconds)
+ **Total running time of the script:** ( 1 minutes 28.694 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 4980344fcc..350d8d0f52 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5396/132723 [00:00<00:02, 53956.45KB/s]
10%|9 | 13029/132723 [00:00<00:01, 67111.49KB/s]
16%|#5 | 20899/132723 [00:00<00:01, 72400.08KB/s]
22%|##1 | 28676/132723 [00:00<00:01, 74516.47KB/s]
27%|##7 | 36457/132723 [00:00<00:01, 75700.96KB/s]
33%|###3 | 44072/132723 [00:00<00:01, 75848.98KB/s]
39%|###9 | 51939/132723 [00:00<00:01, 76768.30KB/s]
45%|####4 | 59616/132723 [00:00<00:00, 76411.92KB/s]
51%|##### | 67258/132723 [00:00<00:00, 75912.21KB/s]
57%|#####6 | 75011/132723 [00:01<00:00, 76405.60KB/s]
62%|######2 | 82653/132723 [00:01<00:00, 76192.77KB/s]
68%|######8 | 90360/132723 [00:01<00:00, 76456.92KB/s]
74%|#######3 | 98031/132723 [00:01<00:00, 76530.52KB/s]
80%|#######9 | 105685/132723 [00:01<00:00, 76523.23KB/s]
86%|########5 | 113516/132723 [00:01<00:00, 77059.64KB/s]
91%|#########
1| 121223/132723 [00:01<00:00, 76882.16KB/s]
97%|#########7| 128912/132723 [00:01<00:00, 76324.25KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75720.39KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5835/132723 [00:00<00:02, 58339.21KB/s]
10%|# | 13751/132723 [00:00<00:01, 70578.12KB/s]
16%|#5 | 20809/132723 [00:00<00:01, 66826.13KB/s]
21%|##1 | 28480/132723 [00:00<00:01, 70598.35KB/s]
27%|##7 | 36292/132723 [00:00<00:01, 73251.80KB/s]
33%|###2 | 43640/132723 [00:00<00:01, 69504.56KB/s]
39%|###8 | 51509/132723 [00:00<00:01, 72360.52KB/s]
45%|####4 | 59435/132723 [00:00<00:00, 74485.83KB/s]
51%|##### | 67365/132723 [00:00<00:00, 75949.74KB/s]
57%|#####6 | 75251/132723 [00:01<00:00, 76830.15KB/s]
63%|######2 | 82996/132723 [00:01<00:00, 77016.52KB/s]
68%|######8 | 90822/132723 [00:01<00:00, 77389.89KB/s]
74%|#######4 | 98761/132723 [00:01<00:00, 77989.35KB/s]
80%|######## | 106622/132723 [00:01<00:00, 78174.24KB/s]
86%|########6 | 114581/132723 [00:01<00:00, 78596.87KB/s]
92%|#########
2| 122475/132723 [00:01<00:00, 78697.05KB/s]
98%|#########8| 130365/132723 [00:01<00:00, 78751.48KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75446.02KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 9.710 seconds)
+ **Total running time of the script:** ( 3 minutes 15.631 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 1fbb2ea009..60dcf6e47a 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
@@ -5,26 +5,26 @@
Computation times
=================
-**14:03.732** total execution time for **how_to_deploy_models** files:
+**14:16.073** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:19.158 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:27.841 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:09.710 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:15.631 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:32.309 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:29.987 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:27.141 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:28.694 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.901 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:09.196 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:01.436 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.319 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.786 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:37.656 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.935 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.647 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.349 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.095 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 2e565a46b9..1c0ab422e3 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipa4a1254e-d23f-4eb8-b12e-e23df81272ca from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip320e388b-277a-4f0b-ae6b-ec3f99ca5729 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 75fcac27d8..8f46debf70 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:49.819** total execution time for **how_to_extend_tvm** files:
+**00:50.106** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:46.176 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:46.474 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.547 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.542 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.089 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.081 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.009 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 3cd3054529..10f73671c4 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 7627us [7627us] (45.21%; 45.21%)
- FoldScaleAxis: 9243us [10us] (54.79%; 54.79%)
- FoldConstant: 9233us [1867us] (54.73%; 99.90%)
- InferType: 7366us [7366us] (43.66%; 79.78%)
+ InferType: 7449us [7449us] (46.51%; 46.51%)
+ FoldScaleAxis: 8567us [8us] (53.49%; 53.49%)
+ FoldConstant: 8560us [1705us] (53.44%; 99.91%)
+ InferType: 6855us [6855us] (42.80%; 80.08%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 7842us [7842us] (46.55%; 46.55%)
- FoldScaleAxis: 9006us [8us] (53.45%; 53.45%)
- FoldConstant: 8998us [1942us] (53.41%; 99.91%)
- InferType: 7056us [7056us] (41.88%; 78.42%)
+ InferType: 6967us [6967us] (44.38%; 44.38%)
+ FoldScaleAxis: 8733us [7us] (55.62%; 55.62%)
+ FoldConstant: 8726us [1759us] (55.58%; 99.92%)
+ InferType: 6967us [6967us] (44.37%; 79.84%)
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 166313e77b..697006e9a7 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 40.890239 ms
+ Convolution: 54.131713 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 f8cbadf2fb..721c33aa1b 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
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.349388 ms
+ conv2d with tensor core: 12.145971 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 c0bf33588c..50c75d8c35 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018808
- Baseline: 3.477266
+ Numpy running time: 0.019645
+ Baseline: 3.467648
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.299790
+ Opt1: 0.336756
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.345378
+ Opt2: 0.351877
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116910
+ Opt3: 0.122706
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109547
+ Opt4: 0.108576
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.112366
+ Opt5: 0.111877
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147864
+ Opt6: 0.148261
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 8c0c2d1af2..5f82872803 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.386** total execution time for **how_to_optimize_operators** files:
+**00:36.008** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.734 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.401 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.566 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.514 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.087 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.093 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index fb23c4840a..8126b9d63e 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:23.015** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:01.394** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:55.884 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:33.158 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.562 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.814 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.666 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:03.048 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.314 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.460 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.347 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.390 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.243 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.525 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index c6ef874c07..7530eb9609 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
@@ -206,13 +206,6 @@ file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- .T
-
-
@@ -247,244 +240,74 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- let cse_var_2: int32 = (rc.outer.outer*1568)
- let cse_var_1: int32 = (rc.outer.outer*288)
+ allocate(conv2d_nchw: Pointer(local float32), float32, [1]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), 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" = 392 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*16)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*16), 81)) && (floormod((threadIdx.x_1*16), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 81)*49)) + (floordiv(floormod((threadIdx.x_1*16), 81), 9)*7)) + floormod((threadIdx.x_1*7), 9)) [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 1), 81)) && (floormod(((threadIdx.x_1*16) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 2)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 2), 81)) && (floormod(((threadIdx.x_1*16) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 3)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 3), 81)) && (floormod(((threadIdx.x_1*16) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 3), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 4)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 4), 81)) && (floormod(((threadIdx.x_1*16) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 5)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 5), 81)) && (floormod(((threadIdx.x_1*16) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 6)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 6), 81)) && (floormod(((threadIdx.x_1*16) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 7)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 7), 81)) && (floormod(((threadIdx.x_1*16) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 8)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 8), 81)) && (floormod(((threadIdx.x_1*16) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 10)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 11)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 12)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 13)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 14)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 14), 81)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 15)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- pad_temp.shared_1[((threadIdx.x_1*16) + 896)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 5), 81)) && (floormod(((threadIdx.x_1*16) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 896), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 897)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 6), 81)) && (floormod(((threadIdx.x_1*16) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 897), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 898)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 7), 81)) && (floormod(((threadIdx.x_1*16) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 898), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 899)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 8), 81)) && (floormod(((threadIdx.x_1*16) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 899), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 900)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 900), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 901)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 901), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 902)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 902), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 903)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 903), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 904)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 904), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 905)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 896), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 905), 81)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 896), 9) + 1), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 906)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 906), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 907)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 16), 81)) && (floormod(((threadIdx.x_1*16) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 907), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 908)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 17), 81)) && (floormod(((threadIdx.x_1*16) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 908), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 17), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 909)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 2), 9)) && (floormod(((threadIdx.x_1*16) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 909), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 2), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 910)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 19), 81)) && (floormod(((threadIdx.x_1*16) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 910), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 19), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 911)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 20), 81)) && (floormod(((threadIdx.x_1*16) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 911), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 20), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ if @tir.likely((threadIdx.x_1 < 120), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1792)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1792), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1793)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1793), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1794)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1794), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1795)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1795), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1796)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 14), 81)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1796), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1797)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1797), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1798)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 16), 81)) && (floormod(((threadIdx.x_1*16) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1798), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1799)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 17), 81)) && (floormod(((threadIdx.x_1*16) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1799), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 17), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1800)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 2), 9)) && (floormod(((threadIdx.x_1*16) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1800), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 2), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1801)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 1792), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1801), 81)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 1792), 9) + 1), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, d [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1802)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 20), 81)) && (floormod(((threadIdx.x_1*16) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1802), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 20), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1803)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 21), 81)) && (floormod(((threadIdx.x_1*16) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1803), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 21), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1804)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 22), 81)) && (floormod(((threadIdx.x_1*16) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1804), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 22), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1805)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 23), 81)) && (floormod(((threadIdx.x_1*16) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1805), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 23), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1806)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 24), 81)) && (floormod(((threadIdx.x_1*16) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1806), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 24), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1807)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 25), 81)) && (floormod(((threadIdx.x_1*16) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1807), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 25), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ if @tir.likely((threadIdx.x_2 < 368), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*3)) + 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_3[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 112), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2) + 168)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 224), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 280), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 336), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 448), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 504), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 72)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 560), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 616), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 672), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 728), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 840), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 88), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 896), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 952), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1008), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1064), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 200), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1120), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1232), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1288), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1344), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 64)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1400), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 248), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1456), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1512), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1624), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 184), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1680), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1736), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1792), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1848), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 40)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1904), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2072), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2128), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2184), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 56)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2240), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel_3[(((((blockIdx.x*36864) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3)) + 32256)]
- }
- for (rc.outer.inner: int32, 0, 16) {
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 90)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 99)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 100)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 92)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 101)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 93)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 102)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 94)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 103)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 95)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 104)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 96)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 105)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- }
+ for (rc.outer.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 35)]))
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*392) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- }
+ compute_3: Buffer(compute_2, float32, [25088], [])[((blockIdx.x*392) + threadIdx.x)] = max((conv2d_nchw_1[0] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*8) + floordiv(threadIdx.x, 49))]), 0f32)
}
}
@@ -538,7 +361,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.258 ms
+ Execution time of this operator: 0.418 ms
@@ -595,13 +418,13 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_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=4)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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 [...]
@@ -614,8 +437,8 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_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)
@@ -635,12 +458,12 @@ 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=392)
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=16)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=392)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -660,194 +483,65 @@ 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) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[2304];
+ extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[1];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 16)] = (((((9 <= ((((int)threadIdx.x) * 16) % 81)) && (((((int)threadIdx.x) * 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 16) / 81) * 49)) + ((((((int)threadIdx.x) * 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1)] = (((((9 <= (((((int)threadIdx.x) * 16) + 1) % 81)) && ((((((int)threadIdx.x) * 16) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 2)] = (((((9 <= (((((int)threadIdx.x) * 16) + 2) % 81)) && ((((((int)threadIdx.x) * 16) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 2) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 3)] = (((((9 <= (((((int)threadIdx.x) * 16) + 3) % 81)) && ((((((int)threadIdx.x) * 16) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 3) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 3) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 4)] = (((((9 <= (((((int)threadIdx.x) * 16) + 4) % 81)) && ((((((int)threadIdx.x) * 16) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 4) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 5)] = (((((9 <= (((((int)threadIdx.x) * 16) + 5) % 81)) && ((((((int)threadIdx.x) * 16) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 5) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 6)] = (((((9 <= (((((int)threadIdx.x) * 16) + 6) % 81)) && ((((((int)threadIdx.x) * 16) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 6) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 7)] = (((((9 <= (((((int)threadIdx.x) * 16) + 7) % 81)) && ((((((int)threadIdx.x) * 16) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 7) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 8)] = (((((9 <= (((((int)threadIdx.x) * 16) + 8) % 81)) && ((((((int)threadIdx.x) * 16) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 8) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 9) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 10)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 10) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 11)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 11) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 12)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 12) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 13)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 13) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 14)] = (((((9 <= (((((int)threadIdx.x) * 16) + 14) % 81)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 14) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 15)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 15) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 896)] = (((((9 <= (((((int)threadIdx.x) * 16) + 5) % 81)) && ((((((int)threadIdx.x) * 16) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 896) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 897)] = (((((9 <= (((((int)threadIdx.x) * 16) + 6) % 81)) && ((((((int)threadIdx.x) * 16) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 897) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 898)] = (((((9 <= (((((int)threadIdx.x) * 16) + 7) % 81)) && ((((((int)threadIdx.x) * 16) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 898) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 899)] = (((((9 <= (((((int)threadIdx.x) * 16) + 8) % 81)) && ((((((int)threadIdx.x) * 16) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 899) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 900)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 900) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 901)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 901) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 902)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 902) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 903)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 903) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 904)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 904) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 905)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 896) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 905) / 81) * 49)) + ((((((((int)threadIdx.x) * 16) + 896) / 9) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 906)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 906) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 907)] = (((((9 <= (((((int)threadIdx.x) * 16) + 16) % 81)) && ((((((int)threadIdx.x) * 16) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 907) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 908)] = (((((9 <= (((((int)threadIdx.x) * 16) + 17) % 81)) && ((((((int)threadIdx.x) * 16) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 908) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 17) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 909)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 2) % 9)) && ((((((int)threadIdx.x) * 16) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 909) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 910)] = (((((9 <= (((((int)threadIdx.x) * 16) + 19) % 81)) && ((((((int)threadIdx.x) * 16) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 910) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 19) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 911)] = (((((9 <= (((((int)threadIdx.x) * 16) + 20) % 81)) && ((((((int)threadIdx.x) * 16) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 911) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 20) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1792)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1792) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1793)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1793) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1794)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1794) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1795)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1795) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1796)] = (((((9 <= (((((int)threadIdx.x) * 16) + 14) % 81)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1796) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 120) {
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1797)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1797) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1798)] = (((((9 <= (((((int)threadIdx.x) * 16) + 16) % 81)) && ((((((int)threadIdx.x) * 16) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1798) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1799)] = (((((9 <= (((((int)threadIdx.x) * 16) + 17) % 81)) && ((((((int)threadIdx.x) * 16) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1799) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 17) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1800)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 2) % 9)) && ((((((int)threadIdx.x) * 16) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1800) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1801)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 1792) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1801) / 81) * 49)) + ((((((((int)threadIdx.x) * 16) + 1792) / 9) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1802)] = (((((9 <= (((((int)threadIdx.x) * 16) + 20) % 81)) && ((((((int)threadIdx.x) * 16) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1802) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 20) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1803)] = (((((9 <= (((((int)threadIdx.x) * 16) + 21) % 81)) && ((((((int)threadIdx.x) * 16) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1803) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 21) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1804)] = (((((9 <= (((((int)threadIdx.x) * 16) + 22) % 81)) && ((((((int)threadIdx.x) * 16) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1804) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 22) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1805)] = (((((9 <= (((((int)threadIdx.x) * 16) + 23) % 81)) && ((((((int)threadIdx.x) * 16) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1805) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 23) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1806)] = (((((9 <= (((((int)threadIdx.x) * 16) + 24) % 81)) && ((((((int)threadIdx.x) * 16) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1806) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 24) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1807)] = (((((9 <= (((((int)threadIdx.x) * 16) + 25) % 81)) && ((((((int)threadIdx.x) * 16) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1807) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 25) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 168)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 224) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 104) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 504) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 216)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 616) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 672) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 728) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 152) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 208) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 840) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 88) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 896) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 952) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1008) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1064) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 200) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1120) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1232) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1288) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 136) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1344) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 192)];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1400) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 248) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1456) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1512) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1624) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 184) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1680) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1736) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1792) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1848) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 120)];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1904) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 232) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2072) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2128) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2184) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 168)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2240) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 224) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 280) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 32256)];
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 368) {
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 100)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 92)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 101)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 93)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 102)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 94)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 103)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 95)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 104)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 96)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 105)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- }
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 35)]));
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- }
+ compute[((((int)blockIdx.x) * 392) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
}
@@ -908,7 +602,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 55.884 seconds)
+ **Total running time of the script:** ( 5 minutes 33.158 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 c6d33e4c12..6255c5f9b7 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.7943 7.7966 7.8039 7.7824 0.0089
+ 7.8856 7.8871 7.8880 7.8816 0.0028
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.666 seconds)
+ **Total running time of the script:** ( 1 minutes 3.048 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index e552f87b15..b298c5c495 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 775.5632 776.7474 777.0366 772.9058 1.8828
+ 761.9076 760.6141 764.6064 760.5022 1.9089
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.562 seconds)
+ **Total running time of the script:** ( 1 minutes 33.814 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 6109819f68..f81b346da6 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
@@ -386,29 +386,79 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [4096], [])[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 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*4096) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 128) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_22] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_22]), 0f32)
+ }
}
}
}
@@ -464,7 +514,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.564 ms
+ Execution time of this operator: 1.722 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 0891b8b854..c668d3e0e4 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:27.503** total execution time for **how_to_tune_with_autotvm** files:
+**00:27.597** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:27.468 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:27.561 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 916db6f69e..3358b34419 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
@@ -265,8 +265,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 90.32/90.32 result: MeasureResult(costs=(0.0025632497906976745,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.293156862258911, timestamp=1672786477.372566) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,484682
- No: 2 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -388,8 +387,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4270075
- No: 3 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6188525
+ No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -511,8 +510,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2675170
- No: 4 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8648012
+ No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -634,9 +633,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4867909
- No: 5 GFLOPS: 7.29/90.32 result: MeasureResult(costs=(0.031743408,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8351917266845703, timestamp=1672786483.410508) [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3992223
- No: 6 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2499392
+ No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -758,8 +756,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 1]), ('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, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10258171
- No: 7 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8564334
+ No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -881,8 +879,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7930421
- No: 8 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1776587
+ No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1004,8 +1002,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3519497
- No: 9 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9355026
+ No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1127,8 +1125,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,191651
- No: 10 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3769498
+ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1250,8 +1248,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5379679
- No: 11 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6404388
+ No: 9 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1373,8 +1371,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10014888
- No: 12 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1101238
+ No: 10 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1496,8 +1494,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9071960
- No: 13 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3113668
+ No: 11 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1619,8 +1617,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1329966
- No: 14 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2115181
+ No: 12 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1742,8 +1740,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6882857
- No: 15 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6878598
+ No: 13 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1865,9 +1863,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,700250
- No: 16 GFLOPS: 44.75/90.32 result: MeasureResult(costs=(0.00517342344,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.082315444946289, timestamp=1672786486.8927758) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7821809
- No: 17 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1485535
+ No: 14 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1989,8 +1986,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3823609
- No: 18 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1518738
+ No: 15 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2112,8 +2109,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4345966
- No: 19 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1638603
+ No: 16 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2235,8 +2232,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8284252
- No: 20 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2766897
+ No: 17 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2358,7 +2355,254 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4736783
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1149175
+ No: 18 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:388
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:374
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:269
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:388
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:374
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:269
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2216305
+ No: 19 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:388
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:374
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:269
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:388
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:374
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:269
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,387066
+ No: 20 GFLOPS: 109.33/109.33 result: MeasureResult(costs=(0.002117441714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.47225284576416, timestamp=1672790261.0809987) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7376821
@@ -2413,9 +2657,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,484682
+ [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7376821
Finish loading 20 records
- Time cost of this operator: 0.002954
+ Time cost of this operator: 0.002111
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 1e15ae9602..aecdcc7778 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.3 98.728 (1, 2, 10, 10, 3) 2 1 [312.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.039 0.961 (1, 6, 10, 10) 1 1 [3.039]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.985 0.312 (1, 1, 10, 10, 3) 1 1 [0.985]
- Total_time - 316.325 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 317.2 98.75 (1, 2, 10, 10, 3) 2 1 [317.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.026 0.942 (1, 6, 10, 10) 1 1 [3.026]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.99 0.308 (1, 1, 10, 10, 3) 1 1 [0.99]
+ Total_time - 321.215 - - - - -
@@ -397,10 +397,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.8 97.574 (1, 6, 10, 10, 1) 2 1 [104.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.754 1.633 (1, 6, 10, 10) 1 1 [1.754]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.852 0.794 (1, 3, 10, 10, 1) 1 1 [0.852]
- Total_time - 107.406 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.509 (1, 6, 10, 10, 1) 2 1 [102.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.783 1.693 (1, 6, 10, 10) 1 1 [1.783]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.798 (1, 3, 10, 10, 1) 1 1 [0.84]
+ Total_time - 105.323 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index de77fe6c48..3eaeebf1cf 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 60.2MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 61.2MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.369 seconds)
+ **Total running time of the script:** ( 1 minutes 5.583 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index f0f6368e73..c3b4171778 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmputeaywft/images/random'
+ '/tmp/tmpefiaqggl/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
+ :alt: [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmputeaywft/images/target contains 8144 images
- /tmp/tmputeaywft/images/random contains 5000 images
+ /tmp/tmpefiaqggl/images/target contains 8144 images
+ /tmp/tmpefiaqggl/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2162 - accuracy: 0.9222 - val_loss: 0.1380 - val_accuracy: 0.9558 - 47s/epoch - 145ms/step
+ 328/328 - 48s - loss: 0.2220 - accuracy: 0.9225 - val_loss: 0.1097 - val_accuracy: 0.9619 - 48s/epoch - 145ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0950 - accuracy: 0.9656 - val_loss: 0.1047 - val_accuracy: 0.9653 - 44s/epoch - 133ms/step
+ 328/328 - 44s - loss: 0.0941 - accuracy: 0.9638 - val_loss: 0.1063 - val_accuracy: 0.9656 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0635 - accuracy: 0.9753 - val_loss: 0.1158 - val_accuracy: 0.9660 - 44s/epoch - 133ms/step
+ 328/328 - 44s - loss: 0.0631 - accuracy: 0.9755 - val_loss: 0.0962 - val_accuracy: 0.9702 - 44s/epoch - 133ms/step
- <keras.callbacks.History object at 0x7f4c62660550>
+ <keras.callbacks.History object at 0x7f28d4a7a290>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 26.200 seconds)
+ **Total running time of the script:** ( 4 minutes 36.821 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index e4db25f1e8..347f117758 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
@@ -5,18 +5,18 @@
Computation times
=================
-**06:34.499** total execution time for **how_to_work_with_microtvm** files:
+**06:48.464** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:26.200 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:36.821 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:04.369 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:05.583 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.975 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:53.956 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.093 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.085 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.860 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.017 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index e9eac45222..e73fb4bb14 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:45.234** total execution time for **how_to_work_with_relay** files:
+**00:46.237** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.993 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:34.297 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.563 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.359 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.671 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.574 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 0d782e100a..0721f899f7 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f4bff34f440>
+ <function my_cuda_math_rule at 0x7f28e0567dd0>
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 5fca64732b..17a40d49de 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:07.484** total execution time for **how_to_work_with_schedules** files:
+**00:06.939** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.919 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.352 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.178 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.183 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.592 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.598 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.573 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.581 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.118 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.119 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.051 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.030 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.025 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 8cce3764fa..9a8ea71ae6 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjhc189pk/input0.cc'\nsource_filename = \"/tmp/tmpjhc189pk/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpy2zohiqq/input0.cc'\nsource_filename = \"/tmp/tmpy2zohiqq/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 2c1b594a59..88b94da82f 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:27.382** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:27.742** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.375 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.735 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 3e5f48017c..1b3bfbf4e2 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 30.65s!
+ resnet18_v1 inference graph built in 31.01s!
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 1b0978a00f..2848f7e541 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 20.27s!
+ yolov3-tiny inference graph built in 20.74s!
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 0c20c8ab2d..d6f86d9e07 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:42.872** total execution time for **topic_vta_tutorials_frontend** files:
+**01:43.872** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.177 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.829 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.695 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:51.043 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index 91cfaca5c4..707c897e2c 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.183** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.226** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.708 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.748 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.475 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.478 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index 77a98770ef..5b1fda7053 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.855** total execution time for **topic_vta_tutorials** files:
+**00:00.845** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.455 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.448 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.400 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.397 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 68110421b8..dfc499f46e 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -325,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.940 ms
+ Execution time of this operator: 100.237 ms
@@ -443,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.124 seconds)
+ **Total running time of the script:** ( 1 minutes 15.424 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index bd2ac9e00d..f2463e2253 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 11.54/11.54 result: MeasureResult(costs=(0.0232534442,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6074883937835693, timestamp=1672785039.2747946) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
- No: 2 GFLOPS: 2.05/11.54 result: MeasureResult(costs=(0.1311131504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3415377140045166, timestamp=1672785042.39668) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
- No: 3 GFLOPS: 10.86/11.54 result: MeasureResult(costs=(0.0247229354,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6333410739898682, timestamp=1672785043.053513) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
- No: 4 GFLOPS: 1.77/11.54 result: MeasureResult(costs=(0.151981095,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.655801296234131, timestamp=1672785046.517171) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
- No: 5 GFLOPS: 12.66/12.66 result: MeasureResult(costs=(0.0212016438,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5941817760467529, timestamp=1672785047.2356257) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
- No: 6 GFLOPS: 12.90/12.90 result: MeasureResult(costs=(0.020816462799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5831103324890137, timestamp=1672785047.8258975) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
- No: 7 GFLOPS: 10.53/12.90 result: MeasureResult(costs=(0.0254842988,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6501202583312988, timestamp=1672785049.2774296) [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
- No: 8 GFLOPS: 1.55/12.90 result: MeasureResult(costs=(0.172636044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0099596977233887, timestamp=1672785052.2972908) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
- No: 9 GFLOPS: 1.22/12.90 result: MeasureResult(costs=(0.2202219296,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7197518348693848, timestamp=1672785056.1386836) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
- No: 10 GFLOPS: 1.17/12.90 result: MeasureResult(costs=(0.22848886680000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.859966993331909, timestamp=1672785060.0476418) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+ No: 1 GFLOPS: 10.25/10.25 result: MeasureResult(costs=(0.026194271199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.664623498916626, timestamp=1672788792.4754536) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
+ No: 2 GFLOPS: 1.08/10.25 result: MeasureResult(costs=(0.2496804558,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.244028806686401, timestamp=1672788796.7307754) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+ No: 3 GFLOPS: 9.72/10.25 result: MeasureResult(costs=(0.027611750400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7044909000396729, timestamp=1672788798.2370958) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
+ No: 4 GFLOPS: 12.18/12.18 result: MeasureResult(costs=(0.0220330818,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.570030689239502, timestamp=1672788799.6622183) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+ No: 5 GFLOPS: 10.31/12.18 result: MeasureResult(costs=(0.0260387062,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.711327314376831, timestamp=1672788800.568145) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+ No: 6 GFLOPS: 2.43/12.18 result: MeasureResult(costs=(0.110456584,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.003021717071533, timestamp=1672788803.3919518) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 7 GFLOPS: 9.82/12.18 result: MeasureResult(costs=(0.027326444999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8071770668029785, timestamp=1672788804.0915456) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
+ No: 8 GFLOPS: 2.75/12.18 result: MeasureResult(costs=(0.0977106252,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8109846115112305, timestamp=1672788805.9069953) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 9 GFLOPS: 8.28/12.18 result: MeasureResult(costs=(0.032406979,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7195665836334229, timestamp=1672788806.7501853) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+ No: 10 GFLOPS: 0.89/12.18 result: MeasureResult(costs=(0.30044604639999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.021171808242798, timestamp=1672788811.8149707) [('tile_y', [-1, 128]), ('tile_x', [-1, 2])],None,17
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 380fb857cc..dafbfc43dc 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 513.194206589999, 'median': 512.949942749998, 'std': 2.1665419819072995}
+ {'mean': 523.192951289999, 'median': 523.8391569499925, 'std': 2.481909805515635}
@@ -554,30 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.60/ 22.54 GFLOPS | Progress: (4/20) | 6.78 s
[Task 1/25] Current/Best: 19.11/ 22.54 GFLOPS | Progress: (8/20) | 10.41 s
[Task 1/25] Current/Best: 12.50/ 22.54 GFLOPS | Progress: (12/20) | 12.55 s
[Task 1/25] Current/Best: 13.47/ 22.54 GFLOPS | Progress: (16/20) | 17.50 s
[Task 1/25] Current/Best: 19.32/ 23.79 GFLOPS | Progress: (20/20) | 19.49 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 6.51/ 19.48 GFLOPS | Progress: (4/20) | 3.21 s
[Task 2/25] Current/Best: 11.73/ 19.48 GFLOPS | Progress: (8/20) | 5.11 s
[Task 2/25] Current/Best: 7.63/ 19.48 GFLOPS | Progress: (12/20) | 8.16 s
[Task 2/25] Current/Best: 16.81/ 19.48 GFLOPS | Progress: (16/20) | 9.92 s
[Task 2/25] Current/Best: 7.18/ 19.48 GFLOPS | Progress: (20/20) | 11.69 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.38/ 14.37 GFLOPS | Progress: (4/20) | 4.92 s
[Task 3/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (8/20) | 7.14 s
[Task 3/25] Current/Best: 10.03/ 21.17 GFLOPS | Progress: (12/20) | 9.85 s
[Task 3/25] Current/Best: 1.62/ 21.17 GFLOPS | Progress: (16/20) | 14.08 s
[Task 3/25] Current/Best: 11.81/ 21.17 GFLOPS | Progress: (20/20) | 16.72 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.79/ 17.55 GFLOPS | Progress: (4/20) | 3.95 s
[Task 4/25] Current/Best: 8.24/ 17.55 GFLOPS | Progress: (8/20) | 6.32 s
[Task 4/25] Current/Best: 15.77/ 21.58 GFLOPS | Progress: (12/20) | 12.19 s
[Task 4/25] Current/Best: 16.53/ 21.58 GFLOPS | Progress: (16/20) | 17.13 s
[Task 4/25] Current/Best: 13.25/ 21.58 GFLOPS | Progress: (20/20) | 21.79 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 3.43/ 15.27 GFLOPS | Progress: (4/20) | 4.05 s
[Task 5/25] Current/Best: 12.14/ 17.98 GFLOPS | Progress: (8/20) | 6.63 s
[Task 5/25] Current/Best: 6.63/ 21.63 GFLOPS | Progress: (12/20) | 8.54 s
[Task 5/25] Current/Best: 18.37/ 21.63 GFLOPS | Progress: (16/20) | 10.61 s
[Task 5/25] Current/Best: 4.77/ 21.63 GFLOPS | Progress: (20/20) | 12.87 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 21.59/ 21.59 GFLOPS | Progress: (4/20) | 5.16 s
[Task 6/25] Current/Best: 11.95/ 21.59 GFLOPS | Progress: (8/20) | 7.10 s
[Task 6/25] Current/Best: 12.55/ 21.59 GFLOPS | Progress: (12/20) | 10.16 s
[Task 6/25] Current/Best: 14.21/ 21.59 GFLOPS | Progress: (16/20) | 15.43 s
[Task 6/25] Current/Best: 10.51/ 21.59 GFLOPS | Progress: (20/20) | 18.17 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.77/ 17.89 GFLOPS | Progress: (4/20) | 4.74 s
[Task 7/25] Current/Best: 9.20/ 17.89 GFLOPS | Progress: (8/20) | 6.92 s
[Task 7/25] Current/Best: 14.81/ 17.89 GFLOPS | Progress: (12/20) | 8.96 s
[Task 7/25] Current/Best: 17.47/ 17.89 GFLOPS | Progress: (16/20) | 11.99 s
[Task 7/25] Current/Best: 16.21/ 17.89 GFLOPS | Progress: (20/20) | 14.54 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 3.81/ 12.59 GFLOPS | Progress: (4/20) | 13.73 s
[Task 8/25] Current/Best: 17.39/ 18.71 GFLOPS | Progress: (8/20) | 17.52 s
[Task 8/25] Current/Best: 2.56/ 19.58 GFLOPS | Progress: (12/20) | 20.72 s
[Task 8/25] Current/Best: 12.34/ 19.58 GFLOPS | Progress: (16/20) | 23.22 s
[Task 8/25] Current/Best: 7.86/ 19.58 GFLOPS | Progress: (20/20) | 27.56 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.34/ 16.44 GFLOPS | Progress: (4/20) | 3.61 s
[Task 9/25] Current/Best: 13.31/ 16.44 GFLOPS | Progress: (8/20) | 5.91 s
[Task 9/25] Current/Best: 6.75/ 19.08 GFLOPS | Progress: (12/20) | 7.65 s
[Task 9/25] Current/Best: 16.05/ 19.08 GFLOPS | Progress: (16/20) | 10.42 s
[Task 9/25] Current/Best: 1.94/ 21.56 GFLOPS | Progress: (20/2
0) | 19.73 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 15.98/ 15.98 GFLOPS | Progress: (4/20) | 4.15 s
[Task 10/25] Current/Best: 12.47/ 15.98 GFLOPS | Progress: (8/20) | 5.99 s
[Task 10/25] Current/Best: 13.77/ 20.67 GFLOPS | Progress: (12/20) | 9.21 s
[Task 10/25] Current/Best: 4.43/ 20.67 GFLOPS | Progress: (16/20) | 11.45 s
[Task 10/25] Current/Best: 8.98/ 20.67 GFLOPS | Progress: (20/20) | 14.14 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.94/ 15.29 GFLOPS | Progress: (4/20) | 4.44 s
[Task 11/25] Current/Best: 19.76/ 19.76 GFLOPS | Progress: (8/20) | 6.69 s
[Task 11/25] Current/Best: 21.08/ 21.08 GFLOPS | Progress: (12/20) | 9.34 s
[Task 11/25] Current/Best: 13.27/ 21.08 GFLOPS | Progress: (16/20) | 13.02 s
[Task 11/25] Current/Best: 21.84/ 21.84 GFLOPS | Progress: (20/20) | 16.91 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.11/ 16.65 GFLOPS | Progress: (4/20) | 8.32 s
[Task 12/25] Current/Best: 8.18/ 16.65 GFLOPS | Progress: (8/20) | 11.36 s
[Task 12/25] Current/Best: 4.51/ 16.65 GFLOPS | Progress: (12/20) | 14.42 s
[Task 12/25] Current/Best: 10.71/ 16.65 GFLOPS | Progress: (16/20) | 17.31 s
[Task 12/25] Current/Best: 4.76/ 17.75 GFLOPS | Progress: (20/20) | 20.31 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.42/ 20.40 GFLOPS | Progress: (4/20) | 4.20 s
[Task 13/25] Current/Best: 15.21/ 20.40 GFLOPS | Progress: (8/20) | 6.43 s
[Task 13/25] Current/Best: 21.06/ 21.06 GFLOPS | Progress: (12/20) | 9.63 s
[Task 13/25] Current/Best: 9.80/ 21.06 GFLOPS | Progress: (16/20) | 12.86 s
[Task 13/25] Current/Best: 12.39/ 21.06 GFLOPS | Progress: (20/20) | 16.16 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.41/ 19.23 GFLOPS | Progress: (4/20) | 4.33 s
[Task 14/25] Current/Best: 3.57/ 19.23 GFLOPS | Progress: (8/20) | 11.10 s
[Task 14/25] Current/Best: 13.18/ 19.23 GFLOPS | Progress: (12/20) | 19.28 s
[Task 14/25] Current/Best: 20.29/ 20.29 GFLOPS | Progress: (16/20) | 21.43 s
[Task 14/25] Current/Best: 4.65/ 20.29 GFLOPS | Progress: (20/20) | 23.52 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.03/ 12.28 GFLOPS | Progress: (4/20) | 9.30 s
[Task 1/25] Current/Best: 16.55/ 16.55 GFLOPS | Progress: (8/20) | 12.52 s
[Task 1/25] Current/Best: 12.73/ 16.55 GFLOPS | Progress: (12/20) | 15.04 s
[Task 1/25] Current/Best: 7.03/ 16.79 GFLOPS | Progress: (16/20) | 17.97 s
[Task 1/25] Current/Best: 12.52/ 22.78 GFLOPS | Progress: (20/20) | 20.86 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.84/ 15.49 GFLOPS | Progress: (4/20) | 3.80 s
[Task 2/25] Current/Best: 6.42/ 15.49 GFLOPS | Progress: (8/20) | 5.50 s
[Task 2/25] Current/Best: 3.27/ 17.76 GFLOPS | Progress: (12/20) | 7.80 s
[Task 2/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (16/20) | 9.17 s
[Task 2/25] Current/Best: 3.66/ 21.00 GFLOPS | Progress: (20/20) | 10.56 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.65/ 16.92 GFLOPS | Progress: (4/20) | 4.71 s
[Task 3/25] Current/Best: 19.85/ 19.91 GFLOPS | Progress: (8/20) | 7.06 s
[Task 3/25] Current/Best: 10.07/ 19.91 GFLOPS | Progress: (12/20) | 9.46 s
[Task 3/25] Current/Best: 14.77/ 19.91 GFLOPS | Progress: (16/20) | 11.97 s
[Task 3/25] Current/Best: 18.14/ 20.00 GFLOPS | Progress: (20/20) | 14.03 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.85/ 19.22 GFLOPS | Progress: (4/20) | 3.82 s
[Task 4/25] Current/Best: 12.01/ 22.39 GFLOPS | Progress: (8/20) | 5.81 s
[Task 4/25] Current/Best: 11.35/ 22.39 GFLOPS | Progress: (12/20) | 8.98 s
[Task 4/25] Current/Best: 17.71/ 22.39 GFLOPS | Progress: (16/20) | 13.81 s
[Task 4/25] Current/Best: 8.76/ 22.39 GFLOPS | Progress: (20/20) | 15.59 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.48/ 13.08 GFLOPS | Progress: (4/20) | 4.59 s
[Task 5/25] Current/Best: 9.86/ 13.08 GFLOPS | Progress: (8/20) | 7.03 s
[Task 5/25] Current/Best: 13.06/ 13.08 GFLOPS | Progress: (12/20) | 9.17 s
[Task 5/25] Current/Best: 9.34/ 13.28 GFLOPS | Progress: (16/20) | 11.44 s
[Task 5/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (20/20) | 13.14 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 4.43/ 15.78 GFLOPS | Progress: (4/20) | 4.41 s
[Task 6/25] Current/Best: 11.42/ 15.78 GFLOPS | Progress: (8/20) | 7.30 s
[Task 6/25] Current/Best: 13.08/ 15.78 GFLOPS | Progress: (12/20) | 10.02 s
[Task 6/25] Current/Best: 10.38/ 16.67 GFLOPS | Progress: (16/20) | 12.45 s
[Task 6/25] Current/Best: 9.43/ 16.67 GFLOPS | Progress: (20/20) | 16.29 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.70/ 16.64 GFLOPS | Progress: (4/20) | 5.10 s
[Task 7/25] Current/Best: 11.83/ 17.73 GFLOPS | Progress: (8/20) | 7.13 s
[Task 7/25] Current/Best: 6.51/ 17.73 GFLOPS | Progress: (12/20) | 9.76 s
[Task 7/25] Current/Best: 12.13/ 17.73 GFLOPS | Progress: (16/20) | 12.57 s
[Task 7/25] Current/Best: 11.67/ 18.98 GFLOPS | Progress: (20/20) | 14.96 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.73/ 21.57 GFLOPS | Progress: (4/20) | 4.77 s
[Task 8/25] Current/Best: 14.19/ 21.57 GFLOPS | Progress: (8/20) | 7.48 s
[Task 8/25] Current/Best: 4.02/ 21.57 GFLOPS | Progress: (12/20) | 11.02 s
[Task 8/25] Current/Best: 2.82/ 21.57 GFLOPS | Progress: (16/20) | 15.35 s
[Task 8/25] Current/Best: 9.92/ 21.57 GFLOPS | Progress: (20/20) | 17.70 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 7.05/ 14.10 GFLOPS | Progress: (4/20) | 7.40 s
[Task 9/25] Current/Best: 15.14/ 16.38 GFLOPS | Progress: (8/20) | 9.45 s
[Task 9/25] Current/Best: 12.33/ 17.20 GFLOPS | Progress: (12/20) | 17.49 s
[Task 9/25] Current/Best: 12.02/ 18.21 GFLOPS | Progress: (16/20) | 19.71 s
[Task 9/25] Current/Best: 10.56/ 18.21 GFLOPS | Progress: (20/20) | 30.81 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (4/20) | 4.52 s
[Task 10/25] Current/Best: 16.33/ 20.62 GFLOPS | Progress: (8/20) | 6.67 s
[Task 10/25] Current/Best: 13.23/ 20.62 GFLOPS | Progress: (12/20) | 8.50 s
[Task 10/25] Current/Best: 12.28/ 20.62 GFLOPS | Progress: (16/20) | 10.53 s
[Task 10/25] Current/Best: 5.53/ 20.62 GFLOPS | Progress: (20/20)
| 12.71 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.24/ 9.24 GFLOPS | Progress: (4/20) | 5.46 s
[Task 11/25] Current/Best: 14.15/ 17.97 GFLOPS | Progress: (8/20) | 8.07 s
[Task 11/25] Current/Best: 13.20/ 17.97 GFLOPS | Progress: (12/20) | 11.30 s
[Task 11/25] Current/Best: 12.91/ 20.33 GFLOPS | Progress: (16/20) | 13.86 s
[Task 11/25] Current/Best: 12.52/ 20.33 GFLOPS | Progress: (20/20) | 17.38 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.36/ 15.36 GFLOPS | Progress: (4/20) | 6.64 s
[Task 12/25] Current/Best: 15.92/ 15.92 GFLOPS | Progress: (8/20) | 10.11 s
[Task 12/25] Current/Best: 18.43/ 18.43 GFLOPS | Progress: (12/20) | 13.32 s
[Task 12/25] Current/Best: 15.25/ 18.43 GFLOPS | Progress: (16/20) | 16.49 s
[Task 12/25] Current/Best: 5.08/ 18.43 GFLOPS | Progress: (20/20) | 19.34 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 16.71/ 17.39 GFLOPS | Progress: (4/20) | 4.31 s
[Task 13/25] Current/Best: 6.65/ 17.39 GFLOPS | Progress: (8/20) | 8.31 s
[Task 13/25] Current/Best: 17.88/ 17.88 GFLOPS | Progress: (12/20) | 10.43 s
[Task 13/25] Current/Best: 7.68/ 17.88 GFLOPS | Progress: (16/20) | 13.50 s
[Task 13/25] Current/Best: 18.04/ 19.37 GFLOPS | Progress: (20/20) | 15.68 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 14.24/ 14.93 GFLOPS | Progress: (4/20) | 4.06 s
[Task 14/25] Current/Best: 10.81/ 17.45 GFLOPS | Progress: (8/20) | 8.81 s
[Task 14/25] Current/Best: 10.26/ 17.45 GFLOPS | Progress: (12/20) | 12.59 s
[Task 14/25] Current/Best: 3.08/ 17.45 GFLOPS | Progress: (16/20) | 17.16 s
[Task 14/25] Current/Best: 11.43/ 17.45 GFLOPS | Progress: (20/20) | 20.19 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 7.46/ 18.81 GFLOPS | Progress: (4/20) | 6.12 s Done.
Done.
-
[Task 15/25] Current/Best: 12.29/ 13.28 GFLOPS | Progress: (4/20) | 4.07 s
[Task 15/25] Current/Best: 5.92/ 16.26 GFLOPS | Progress: (8/20) | 7.76 s
[Task 15/25] Current/Best: 6.76/ 16.26 GFLOPS | Progress: (12/20) | 10.03 s
[Task 15/25] Current/Best: 2.64/ 18.90 GFLOPS | Progress: (16/20) | 14.60 s
[Task 15/25] Current/Best: 5.72/ 18.90 GFLOPS | Progress: (20/20) | 17.33 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 10.56/ 18.96 GFLOPS | Progress: (4/20) | 5.02 s
[Task 16/25] Current/Best: 13.45/ 18.96 GFLOPS | Progress: (8/20) | 6.74 s
[Task 16/25] Current/Best: 8.52/ 18.96 GFLOPS | Progress: (12/20) | 9.31 s
[Task 16/25] Current/Best: 16.10/ 18.96 GFLOPS | Progress: (16/20) | 11.11 s
[Task 16/25] Current/Best: 15.28/ 18.96 GFLOPS | Progress: (20/20) | 14.98 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 15.14/ 20.68 GFLOPS | Progress: (4/20) | 4.00 s
[Task 17/25] Current/Best: 12.30/ 20.68 GFLOPS | Progress: (8/20) | 6.58 s
[Task 17/25] Current/Best: 22.72/ 22.72 GFLOPS | Progress: (12/20) | 9.59 s
[Task 17/25] Current/Best: 23.60/ 23.60 GFLOPS | Progress: (16/20) | 12.30 s
[Task 17/25] Current/Best: 17.81/ 23.60 GFLOPS | Progress: (20/20) | 15.32 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 19.25/ 21.38 GFLOPS | Progress: (4/20) | 4.69 s
[Task 18/25] Current/Best: 10.27/ 21.38 GFLOPS | Progress: (8/20) | 9.08 s
[Task 18/25] Current/Best: 17.93/ 21.38 GFLOPS | Progress: (12/20) | 13.11 s
[Task 18/25] Current/Best: 10.33/ 21.38 GFLOPS | Progress: (16/20) | 19.04 s
[Task 18/25] Current/Best: 16.35/ 21.38 GFLOPS | Progress: (20/20) | 25.13 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.64/ 10.64 GFLOPS | Progress: (4/20) | 6.22 s
[Task 19/25] Current/Best: 17.15/ 17.15 GFLOPS | Progress: (8/20) | 8.67 s
[Task 19/25] Current/Best: 7.10/ 17.15 GFLOPS | Progress: (12/20) | 12.44 s
[Task 19/25] Current/Best: 6.61/ 21.29 GFLOPS | Progress: (16/20) | 16.15 s
[Task 19/25] Current/Best: 9.34/ 21.29 GFLOPS | Progress: (20/20) | 20.84 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 11.18/ 11.18 GFLOPS | Progress: (4/20) | 4.27 s
[Task 20/25] Current/Best: 16.83/ 16.83 GFLOPS | Progress: (8/20) | 7.54 s
[Task 20/25] Current/Best: 2.06/ 16.83 GFLOPS | Progress: (12/20) | 11.75 s
[Task 20/25] Current/Best: 15.20/ 16.83 GFLOPS | Progress: (16/20) | 13.91 s
[Task 20/25] Current/Best: 13.35/ 16.83 GFLOPS | Progress: (20/20) | 17.13 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 19.85/ 19.85 GFLOPS | Progress: (4/20) | 3.41 s
[Task 21/25] Current/Best: 19.51/ 19.85 GFLOPS | Progress: (8/20) | 5.52 s
[Task 21/25] Current/Best: 13.60/ 19.85 GFLOPS | Progress: (12/20) | 7.75 s
[Task 21/25] Current/Best: 11.89/ 19.85 GFLOPS | Progress: (16/20) | 10.30 s
[Task 21/25] Current/Best: 16.12/ 19.85 GFLOPS | Progress: (20/20) | 11.86 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 6.31/ 16.08 GFLOPS | Progress: (4/20) | 4.34 s
[Task 22/25] Current/Best: 7.96/ 16.08 GFLOPS | Progress: (8/20) | 6.05 s
[Task 22/25] Current/Best: 11.26/ 16.14 GFLOPS | Progress: (12/20) | 8.24 s
[Task 22/25] Current/Best: 9.32/ 21.96 GFLOPS | Progress: (16/20) | 10.08 s
[Task 22/25] Current/Best: 5.18/ 21.96 GFLOPS | Progress: (20/20)
| 11.74 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 3.08/ 9.55 GFLOPS | Progress: (4/20) | 6.13 s
[Task 23/25] Current/Best: 16.46/ 20.03 GFLOPS | Progress: (8/20) | 9.56 s
[Task 23/25] Current/Best: 18.69/ 22.24 GFLOPS | Progress: (12/20) | 12.88 s
[Task 23/25] Current/Best: 23.13/ 23.13 GFLOPS | Progress: (16/20) | 16.56 s
[Task 23/25] Current/Best: 8.93/ 23.13 GFLOPS | Progress: (20/20) | 19.70 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 10.16/ 10.16 GFLOPS | Progress: (4/20) | 12.19 s
[Task 24/25] Current/Best: 9.51/ 10.16 GFLOPS | Progress: (8/20) | 24.04 s Done.
-
[Task 24/25] Current/Best: 3.50/ 10.16 GFLOPS | Progress: (12/20) | 36.25 s
[Task 24/25] Current/Best: 4.56/ 10.16 GFLOPS | Progress: (16/20) | 47.19 s
[Task 24/25] Current/Best: 3.72/ 10.16 GFLOPS | Progress: (20/20) | 58.18 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 3.88/ 5.21 GFLOPS | Progress: (4/20) | 13.41 s
[Task 25/25] Current/Best: 7.94/ 8.47 GFLOPS | Progress: (8/20) | 16.18 s
[Task 25/25] Current/Best: 9.10/ 9.10 GFLOPS | Progress: (12/20) | 21.67 s
[Task 25/25] Current/Best: 5.74/ 9.10 GFLOPS | Progress: (16/20) | 27.23 s
[Task 25/25] Current/Best: 7.48/ 9.10 GFLOPS | Progress: (20/20) | 31.22 s Done.
-
+
[Task 15/25] Current/Best: 3.15/ 18.81 GFLOPS | Progress: (8/20) | 11.56 s
[Task 15/25] Current/Best: 7.37/ 18.81 GFLOPS | Progress: (12/20) | 21.51 s
[Task 15/25] Current/Best: 19.48/ 20.76 GFLOPS | Progress: (16/20) | 24.95 s
[Task 15/25] Current/Best: 15.97/ 20.76 GFLOPS | Progress: (20/20) | 30.85 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 17.02/ 18.31 GFLOPS | Progress: (4/20) | 4.84 s
[Task 16/25] Current/Best: 3.01/ 20.82 GFLOPS | Progress: (8/20) | 6.91 s
[Task 16/25] Current/Best: 16.19/ 20.82 GFLOPS | Progress: (12/20) | 8.38 s
[Task 16/25] Current/Best: 6.21/ 20.82 GFLOPS | Progress: (16/20) | 10.76 s
[Task 16/25] Current/Best: 5.09/ 20.82 GFLOPS | Progress: (20/20) | 14.26 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.82/ 20.77 GFLOPS | Progress: (4/20) | 4.46 s
[Task 17/25] Current/Best: 14.17/ 20.77 GFLOPS | Progress: (8/20) | 7.64 s
[Task 17/25] Current/Best: 7.66/ 20.77 GFLOPS | Progress: (12/20) | 10.35 s
[Task 17/25] Current/Best: 18.84/ 20.77 GFLOPS | Progress: (16/20) | 12.35 s
[Task 17/25] Current/Best: 14.93/ 20.77 GFLOPS | Progress: (20/20) | 14.78 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 15.81/ 19.65 GFLOPS | Progress: (4/20) | 5.52 s
[Task 18/25] Current/Best: 11.98/ 19.65 GFLOPS | Progress: (8/20) | 8.21 s
[Task 18/25] Current/Best: 9.64/ 19.65 GFLOPS | Progress: (12/20) | 13.42 s
[Task 18/25] Current/Best: 6.22/ 19.65 GFLOPS | Progress: (16/20) | 17.29 s
[Task 18/25] Current/Best: 18.69/ 19.65 GFLOPS | Progress: (20/20) | 19.58 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.35/ 12.57 GFLOPS | Progress: (4/20) | 5.79 s
[Task 19/25] Current/Best: 5.23/ 18.96 GFLOPS | Progress: (8/20) | 10.01 s
[Task 19/25] Current/Best: 10.84/ 18.96 GFLOPS | Progress: (12/20) | 13.56 s
[Task 19/25] Current/Best: 14.41/ 23.22 GFLOPS | Progress: (16/20) | 17.61 s
[Task 19/25] Current/Best: 3.08/ 23.22 GFLOPS | Progress: (20/20) | 20.97 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 13.69/ 18.53 GFLOPS | Progress: (4/20) | 4.07 s
[Task 20/25] Current/Best: 7.35/ 18.53 GFLOPS | Progress: (8/20) | 7.77 s
[Task 20/25] Current/Best: 12.26/ 18.53 GFLOPS | Progress: (12/20) | 9.93 s
[Task 20/25] Current/Best: 12.21/ 18.53 GFLOPS | Progress: (16/20) | 13.07 s
[Task 20/25] Current/Best: 10.53/ 18.53 GFLOPS | Progress: (20/20) | 16.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 10.51/ 12.00 GFLOPS | Progress: (4/20) | 3.42 s
[Task 21/25] Current/Best: 16.73/ 17.81 GFLOPS | Progress: (8/20) | 5.63 s Done.
+
[Task 21/25] Current/Best: 21.95/ 21.95 GFLOPS | Progress: (12/20) | 8.65 s
[Task 21/25] Current/Best: 19.18/ 21.95 GFLOPS | Progress: (16/20) | 10.64 s
[Task 21/25] Current/Best: 17.10/ 21.95 GFLOPS | Progress: (20/20) | 13.23 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 17.55/ 18.17 GFLOPS | Progress: (4/20) | 3.74 s
[Task 22/25] Current/Best: 9.62/ 18.17 GFLOPS | Progress: (8/20) | 7.59 s
[Task 22/25] Current/Best: 12.15/ 18.17 GFLOPS | Progress: (12/20) | 10.82 s
[Task 22/25] Current/Best: 15.39/ 18.17 GFLOPS | Progress: (16/20) | 12.83 s
[Task 22/25] Current/Best: 13.97/ 18.17 GFLOPS | Progress: (20/20) | 18.37 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 9.45/ 17.77 GFLOPS | Progress: (4/20) | 5.70 s
[Task 23/25] Current/Best: 8.21/ 19.36 GFLOPS | Progress: (8/20) | 8.98 s
[Task 23/25] Current/Best: 2.38/ 19.36 GFLOPS | Progress: (12/20) | 12.63 s
[Task 23/25] Current/Best: 18.59/ 22.40 GFLOPS | Progress: (16/20) | 14.97 s
[Task 23/25] Current/Best: 11.10/ 22.40 GFLOPS | Progress: (20/20) | 19.25 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.37/ 9.71 GFLOPS | Progress: (4/20) | 12.84 s
[Task 24/25] Current/Best: 5.35/ 9.71 GFLOPS | Progress: (8/20) | 24.65 s
[Task 24/25] Current/Best: 2.18/ 9.71 GFLOPS | Progress: (12/20) | 36.23 s
[Task 24/25] Current/Best: 1.66/ 9.71 GFLOPS | Progress: (16/20) | 48.15 s
[Task 24/25] Current/Best: 5.77/ 9.71 GFLOPS | Progress: (20/20) | 60.07 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 25/25] Current/Best: 2.96/ 8.22 GFLOPS | Progress: (4/20) | 13.87 s
[Task 25/25] Current/Best: 1.54/ 9.09 GFLOPS | Progress: (8/20) | 16.07 s
[Task 25/25] Current/Best: 7.50/ 9.09 GFLOPS | Progress: (12/20) | 27.01 s
[Task 25/25] Current/Best: 7.97/ 9.09 GFLOPS | Progress: (16/20) | 29.54 s
[Task 25/25] Current/Best: 2.96/ 9.09 GFLOPS | Progress: (20/20) | 39.91 s
@@ -673,7 +674,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123045 tabby, tabby cat' with probability=0.621104
class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -731,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 411.8653575500002, 'median': 411.6579371999933, 'std': 2.2107734226906803}
- unoptimized: {'mean': 513.194206589999, 'median': 512.949942749998, 'std': 2.1665419819072995}
+ optimized: {'mean': 434.05912445999775, 'median': 433.28455185001076, 'std': 2.978056187539585}
+ unoptimized: {'mean': 523.192951289999, 'median': 523.8391569499925, 'std': 2.481909805515635}
@@ -755,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 47.427 seconds)
+ **Total running time of the script:** ( 12 minutes 4.273 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 be44a6fb8f..bcdc7a94d7 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.26e-07 secs/op
+ 1.244e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 9cbf60fb78..ee07e90577 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x213d8c10)), stage(b, placeholder(b, 0x28371bf0)), 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, 0x24556490)), stage(b, placeholder(b, 0x12a65690)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 6eafce50bc..c8d9daa7d4 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**15:04.807** total execution time for **tutorial** files:
+**15:24.298** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:47.427 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:04.273 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:13.124 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:15.424 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.694 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.845 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.372 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.940 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.721 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.413 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.450 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.349 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.835 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.855 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.173 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.189 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 5c24f3ea9f..a4e2a42be9 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,8 +294,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000009
+ Numpy running time: 0.000007
+ naive: 0.000007
@@ -448,7 +448,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000027
@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, [n: int32], [stride: int32], type="auto"),
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.5752199995804405e-06 1.0
- naive 8.6728e-06 1.14489084151752
- parallel 6.9837000000000006e-06 0.9219138190556576
- vector 2.45603e-05 3.242189665958255
+ numpy 6.524820000777254e-06 1.0
+ naive 6.7542e-06 1.0351549926580996
+ parallel 6.9875000000000004e-06 1.0709107682920955
+ vector 2.65005e-05 4.0614913510017425
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018597
+ Numpy running time: 0.019067
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.467281
+ none: 3.478545
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.293226
+ blocking: 0.333455
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.333874
+ vectorization: 0.355765
@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, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.117445
+ loop permutation: 0.137987
@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, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109663
+ array packing: 0.110269
@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, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111546
+ block caching: 0.112124
@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, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.148143
+ parallelization: 0.147456
@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, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4672807165000004 1.0
- blocking 0.2932257556 0.0845693728242439
- vectorization 0.3338737371 0.09629267555729504
- loop permutation 0.11744508470000001 0.0338723900090078
- array packing 0.1096628929 0.031627924551403994
- block caching 0.1115455265 0.032170895759659784
- parallelization 0.1481426293 0.0427258827342773
+ none 3.4785447568000003 1.0
+ blocking 0.333455125 0.09586052453347005
+ vectorization 0.3557646123 0.10227397868161303
+ loop permutation 0.1379866034 0.03966791087861043
+ array packing 0.11026868370000001 0.03169965931426994
+ block caching 0.1121242066 0.03223307861162777
+ parallelization 0.14745647580000001 0.04239027700067568
@@ -1654,7 +1654,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.694 seconds)
+ **Total running time of the script:** ( 1 minutes 2.845 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index bde4649daf..5f1ba90026 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-e24d4fb78bcc3dd6d450aff0d715e6390a1d70c8
+45a8a44b862a8653a9a20f94dcd924ad968c9595
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index cb2ce93d88..e553822fb1 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.145 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.326 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 9deeaefe9d..7b5f781e41 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip0e64d359-98b4-4749-ab70-1d130b09aff1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip9928348d-f117-4a1a-959d-7d8c9e117ef4 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index c0cfc8f203..1642b35792 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,13 +448,12 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 43.4MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 46.7MB/s]
- 45%|####5 | 18.8M/41.5M [00:00<00:00, 41.1MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 42.6MB/s]
- 80%|######## | 33.3M/41.5M [00:00<00:00, 58.3MB/s]
- 94%|#########4| 39.2M/41.5M [00:00<00:00, 45.8MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 45.0MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 51.7MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 56.0MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 58.1MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 65.5MB/s]
+ 96%|#########6| 40.0M/41.5M [00:00<00:00, 63.7MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 63.3MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 8da0a91b1f..4a30fb2989 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,10 +431,10 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 27%|##7 | 12.3M/44.7M [00:00<00:00, 129MB/s]
- 55%|#####4 | 24.6M/44.7M [00:00<00:00, 109MB/s]
- 79%|#######8 | 35.2M/44.7M [00:00<00:00, 106MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
+ 31%|### | 13.8M/44.7M [00:00<00:00, 144MB/s]
+ 62%|######1 | 27.5M/44.7M [00:00<00:00, 110MB/s]
+ 86%|########6 | 38.5M/44.7M [00:00<00:00, 81.5MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 96.6MB/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 a0a0db76b4..8bdba0b61a 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ 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 13.144 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.391 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index b54b9cdd84..a8cb8e22c2 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:47.707</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:55.977</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:13.144</p></td>
+<td><p>01:15.391</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:11.145</p></td>
+<td><p>01:11.326</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:47.172</p></td>
+<td><p>00:49.560</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:33.042</p></td>
+<td><p>00:33.223</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:29.305</p></td>
+<td><p>00:29.727</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:26.788</p></td>
+<td><p>00:27.609</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.394</p></td>
+<td><p>00:25.919</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:22.499</p></td>
+<td><p>00:23.169</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:16.771</p></td>
+<td><p>00:17.580</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.446</p></td>
+<td><p>00:02.473</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 0f6b82da21..38f8e68409 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,10 +919,9 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 3342.0276 3342.0027 3347.9278 3338.6830 2.7855
+ 2689.6413 2689.0762 2692.5543 2687.0643 1.9732
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.436 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/2387d8448da213eb625e6b3d916327d4/deploy_model_on_adreno.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_model_on_adreno.py</span></code></a></p>
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 64c12c7b83..43dfb1fb12 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1540 16.1293 16.4871 15.9801 0.1393
+ 17.1583 17.2891 17.5560 16.5525 0.3264
</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 fd083e1133..5be7373e4c 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,22 +453,21 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 5%|4 | 8.12M/170M [00:00<00:02, 79.1MB/s]
- 9%|9 | 15.7M/170M [00:00<00:02, 60.6MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:01, 132MB/s]
- 32%|###1 | 53.8M/170M [00:00<00:00, 136MB/s]
- 40%|###9 | 67.5M/170M [00:00<00:00, 121MB/s]
- 47%|####6 | 79.7M/170M [00:00<00:00, 114MB/s]
- 54%|#####3 | 91.0M/170M [00:00<00:00, 105MB/s]
- 60%|###### | 102M/170M [00:00<00:00, 108MB/s]
- 66%|######6 | 113M/170M [00:01<00:00, 102MB/s]
- 72%|#######2 | 123M/170M [00:01<00:00, 98.2MB/s]
- 78%|#######7 | 132M/170M [00:01<00:00, 89.5MB/s]
- 83%|########2 | 141M/170M [00:01<00:00, 87.9MB/s]
- 88%|########7 | 149M/170M [00:01<00:00, 67.0MB/s]
- 93%|#########3| 158M/170M [00:01<00:00, 68.4MB/s]
- 99%|#########8| 168M/170M [00:01<00:00, 74.5MB/s]
-100%|##########| 170M/170M [00:01<00:00, 92.4MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:00, 164MB/s]
+ 19%|#8 | 31.6M/170M [00:00<00:01, 118MB/s]
+ 26%|##5 | 43.6M/170M [00:00<00:01, 114MB/s]
+ 32%|###2 | 54.8M/170M [00:00<00:01, 108MB/s]
+ 38%|###8 | 65.2M/170M [00:00<00:01, 98.9MB/s]
+ 45%|####5 | 76.9M/170M [00:00<00:00, 106MB/s]
+ 51%|#####1 | 87.1M/170M [00:00<00:00, 104MB/s]
+ 57%|#####7 | 97.2M/170M [00:01<00:00, 83.4MB/s]
+ 64%|######4 | 109M/170M [00:01<00:00, 92.9MB/s]
+ 73%|#######3 | 124M/170M [00:01<00:00, 111MB/s]
+ 80%|#######9 | 135M/170M [00:01<00:00, 107MB/s]
+ 86%|########6 | 146M/170M [00:01<00:00, 102MB/s]
+ 92%|#########2| 157M/170M [00:01<00:00, 104MB/s]
+ 98%|#########8| 167M/170M [00:01<00:00, 103MB/s]
+100%|##########| 170M/170M [00:01<00:00, 103MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -566,7 +565,7 @@ 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 19.158 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 27.841 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index ef920632c6..c3acbdf448 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 41.5MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 58.7MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 82.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 96.4MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +589,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4580 90.4380 90.9870 90.0762 0.1651
+ 90.5616 90.5090 92.7981 90.1705 0.3468
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +628,7 @@ 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 6.901 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.196 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index f59c81863b..0fbf25c121 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.4326 121.4678 123.0171 120.2928 0.5353
+ 121.0469 120.9888 122.4999 120.1383 0.4405
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.309 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 29.987 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index bde532cdb9..2c3332fae9 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 27.141 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 28.694 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 3c62fb398b..7d318eb168 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,24 +462,24 @@ 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%|4 | 5396/132723 [00:00<00:02, 53956.45KB/s]
- 10%|9 | 13029/132723 [00:00<00:01, 67111.49KB/s]
- 16%|#5 | 20899/132723 [00:00<00:01, 72400.08KB/s]
- 22%|##1 | 28676/132723 [00:00<00:01, 74516.47KB/s]
- 27%|##7 | 36457/132723 [00:00<00:01, 75700.96KB/s]
- 33%|###3 | 44072/132723 [00:00<00:01, 75848.98KB/s]
- 39%|###9 | 51939/132723 [00:00<00:01, 76768.30KB/s]
- 45%|####4 | 59616/132723 [00:00<00:00, 76411.92KB/s]
- 51%|##### | 67258/132723 [00:00<00:00, 75912.21KB/s]
- 57%|#####6 | 75011/132723 [00:01<00:00, 76405.60KB/s]
- 62%|######2 | 82653/132723 [00:01<00:00, 76192.77KB/s]
- 68%|######8 | 90360/132723 [00:01<00:00, 76456.92KB/s]
- 74%|#######3 | 98031/132723 [00:01<00:00, 76530.52KB/s]
- 80%|#######9 | 105685/132723 [00:01<00:00, 76523.23KB/s]
- 86%|########5 | 113516/132723 [00:01<00:00, 77059.64KB/s]
- 91%|#########1| 121223/132723 [00:01<00:00, 76882.16KB/s]
- 97%|#########7| 128912/132723 [00:01<00:00, 76324.25KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75720.39KB/s]
+ 4%|4 | 5835/132723 [00:00<00:02, 58339.21KB/s]
+ 10%|# | 13751/132723 [00:00<00:01, 70578.12KB/s]
+ 16%|#5 | 20809/132723 [00:00<00:01, 66826.13KB/s]
+ 21%|##1 | 28480/132723 [00:00<00:01, 70598.35KB/s]
+ 27%|##7 | 36292/132723 [00:00<00:01, 73251.80KB/s]
+ 33%|###2 | 43640/132723 [00:00<00:01, 69504.56KB/s]
+ 39%|###8 | 51509/132723 [00:00<00:01, 72360.52KB/s]
+ 45%|####4 | 59435/132723 [00:00<00:00, 74485.83KB/s]
+ 51%|##### | 67365/132723 [00:00<00:00, 75949.74KB/s]
+ 57%|#####6 | 75251/132723 [00:01<00:00, 76830.15KB/s]
+ 63%|######2 | 82996/132723 [00:01<00:00, 77016.52KB/s]
+ 68%|######8 | 90822/132723 [00:01<00:00, 77389.89KB/s]
+ 74%|#######4 | 98761/132723 [00:01<00:00, 77989.35KB/s]
+ 80%|######## | 106622/132723 [00:01<00:00, 78174.24KB/s]
+ 86%|########6 | 114581/132723 [00:01<00:00, 78596.87KB/s]
+ 92%|#########2| 122475/132723 [00:01<00:00, 78697.05KB/s]
+ 98%|#########8| 130365/132723 [00:01<00:00, 78751.48KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 75446.02KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -518,7 +518,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 9.710 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 15.631 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 067c02823d..07f13ed78f 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:03.732</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>14:16.073</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:19.158</p></td>
+<td><p>03:27.841</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:09.710</p></td>
+<td><p>03:15.631</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:32.309</p></td>
+<td><p>02:29.987</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:27.141</p></td>
+<td><p>01:28.694</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:06.901</p></td>
+<td><p>01:09.196</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>01:01.436</p></td>
+<td><p>00:54.319</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:35.786</p></td>
+<td><p>00:37.656</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.935</p></td>
+<td><p>00:26.647</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:25.349</p></td>
+<td><p>00:26.095</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index b13913165c..63422d7e0c 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipa4a1254e-d23f-4eb8-b12e-e23df81272ca 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.zip320e388b-277a-4f0b-ae6b-ec3f99ca5729 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index a63e8b08a7..e348a3c9c2 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:49.819</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:50.106</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:46.176</p></td>
+<td><p>00:46.474</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.547</p></td>
+<td><p>00:02.542</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.089</p></td>
+<td><p>00:01.081</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 65ac243bd1..5450a23f4b 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7627us [7627us] (45.21%; 45.21%)
-FoldScaleAxis: 9243us [10us] (54.79%; 54.79%)
- FoldConstant: 9233us [1867us] (54.73%; 99.90%)
- InferType: 7366us [7366us] (43.66%; 79.78%)
+InferType: 7449us [7449us] (46.51%; 46.51%)
+FoldScaleAxis: 8567us [8us] (53.49%; 53.49%)
+ FoldConstant: 8560us [1705us] (53.44%; 99.91%)
+ InferType: 6855us [6855us] (42.80%; 80.08%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7842us [7842us] (46.55%; 46.55%)
-FoldScaleAxis: 9006us [8us] (53.45%; 53.45%)
- FoldConstant: 8998us [1942us] (53.41%; 99.91%)
- InferType: 7056us [7056us] (41.88%; 78.42%)
+InferType: 6967us [6967us] (44.38%; 44.38%)
+FoldScaleAxis: 8733us [7us] (55.62%; 55.62%)
+ FoldConstant: 8726us [1759us] (55.58%; 99.92%)
+ InferType: 6967us [6967us] (44.37%; 79.84%)
</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 088a3855e4..a54bd026e3 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.890239 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.131713 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index 0364348721..12d99137c7 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.349388 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.145971 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 10d133248f..e547f36194 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018808
-Baseline: 3.477266
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019645
+Baseline: 3.467648
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.299790
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.336756
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.345378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.351877
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116910
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.122706
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109547
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108576
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112366
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111877
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147864
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148261
</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 db6af6a714..b81ac3c47f 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.386</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:36.008</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.734</p></td>
+<td><p>00:33.401</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.566</p></td>
+<td><p>00:01.514</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.087</p></td>
+<td><p>00:01.093</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index ee3855fc2f..c613a7809c 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:23.015</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:01.394</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:55.884</p></td>
+<td><p>05:33.158</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:33.562</p></td>
+<td><p>01:33.814</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:02.666</p></td>
+<td><p>01:03.048</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:27.314</p></td>
+<td><p>00:27.460</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.347</p></td>
+<td><p>00:12.390</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.243</p></td>
+<td><p>00:11.525</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 4060e34ed4..f27f8dbe0b 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
@@ -488,9 +488,6 @@ file and apply it.</p>
<span class="k">del</span> <span class="n">measure_ctx</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
-</pre></div>
-</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.</p>
@@ -507,244 +504,74 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- let cse_var_2: int32 = (rc.outer.outer*1568)
- let cse_var_1: int32 = (rc.outer.outer*288)
+ allocate(conv2d_nchw: Pointer(local float32), float32, [1]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), 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" = 392 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*16)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*16), 81)) && (floormod((threadIdx.x_1*16), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 81)*49)) + (floordiv(floormod((threadIdx.x_1*16), 81), [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 1), 81)) && (floormod(((threadIdx.x_1*16) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 2)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 2), 81)) && (floormod(((threadIdx.x_1*16) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 3)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 3), 81)) && (floormod(((threadIdx.x_1*16) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 3), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 4)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 4), 81)) && (floormod(((threadIdx.x_1*16) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 5)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 5), 81)) && (floormod(((threadIdx.x_1*16) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 6)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 6), 81)) && (floormod(((threadIdx.x_1*16) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 7)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 7), 81)) && (floormod(((threadIdx.x_1*16) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 8)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 8), 81)) && (floormod(((threadIdx.x_1*16) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 10)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dt [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 11)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dt [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 12)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dt [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 13)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dt [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 14)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 14), 81)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dt [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 15)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dt [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- pad_temp.shared_1[((threadIdx.x_1*16) + 896)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 5), 81)) && (floormod(((threadIdx.x_1*16) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 896), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dty [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 897)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 6), 81)) && (floormod(((threadIdx.x_1*16) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 897), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dty [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 898)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 7), 81)) && (floormod(((threadIdx.x_1*16) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 898), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dty [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 899)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 8), 81)) && (floormod(((threadIdx.x_1*16) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 899), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dty [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 900)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 900), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 901)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 901), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 902)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 902), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 903)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 903), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 904)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 904), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 905)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 896), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 905), 81)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 896), 9) + 1), 9)*7)) + floormod(((threadIdx.x_1*7 [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 906)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 906), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 907)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 16), 81)) && (floormod(((threadIdx.x_1*16) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 907), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 908)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 17), 81)) && (floormod(((threadIdx.x_1*16) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 908), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 17), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 909)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 2), 9)) && (floormod(((threadIdx.x_1*16) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 909), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 2), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 910)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 19), 81)) && (floormod(((threadIdx.x_1*16) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 910), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 19), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 911)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 20), 81)) && (floormod(((threadIdx.x_1*16) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 911), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 20), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ if @tir.likely((threadIdx.x_1 < 120), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1792)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1792), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1793)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1793), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1794)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1794), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1795)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1795), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1796)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 14), 81)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1796), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1797)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1797), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1798)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 16), 81)) && (floormod(((threadIdx.x_1*16) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1798), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1799)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 17), 81)) && (floormod(((threadIdx.x_1*16) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1799), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 17), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1800)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 2), 9)) && (floormod(((threadIdx.x_1*16) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1800), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 2), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1801)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 1792), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1801), 81)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 1792), 9) + 1), 9)*7)) + floormod(((threadIdx [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1802)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 20), 81)) && (floormod(((threadIdx.x_1*16) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1802), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 20), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1803)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 21), 81)) && (floormod(((threadIdx.x_1*16) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1803), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 21), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1804)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 22), 81)) && (floormod(((threadIdx.x_1*16) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1804), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 22), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1805)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 23), 81)) && (floormod(((threadIdx.x_1*16) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1805), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 23), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1806)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 24), 81)) && (floormod(((threadIdx.x_1*16) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1806), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 24), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 1807)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 25), 81)) && (floormod(((threadIdx.x_1*16) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1807), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 25), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f [...]
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ if @tir.likely((threadIdx.x_2 < 368), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel_3[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*3)) + 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_3[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 112), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel_3[((((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2) + 168)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 224), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 280), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 336), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 448), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 504), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 72)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 560), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 616), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 672), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 728), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 840), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 88), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 896), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 952), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1008), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1064), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 200), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1120), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1232), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1288), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1344), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 64)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1400), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 248), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1456), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1512), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1624), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 184), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1680), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1736), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1792), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1848), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 40)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1904), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2072), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2128), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2184), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 56)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 2240), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel_3[(((((blockIdx.x*36864) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3)) + 32256)]
- }
- for (rc.outer.inner: int32, 0, 16) {
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 90)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 99)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 100)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 92)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 101)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 93)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 102)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 94)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 103)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 95)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 104)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 96)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 105)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*18)) + rx.outer.inner) + 15)]))
- }
+ for (rc.outer.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*324) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*36)) + 35)]))
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*392) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- }
+ compute_3: Buffer(compute_2, float32, [25088], [])[((blockIdx.x*392) + threadIdx.x)] = max((conv2d_nchw_1[0] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*8) + floordiv(threadIdx.x, 49))]), 0f32)
}
}
</pre></div>
@@ -780,7 +607,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.258 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.418 ms
</pre></div>
</div>
</div>
@@ -818,13 +645,13 @@ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_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=4)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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 [...]
@@ -837,8 +664,8 @@ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_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)
@@ -858,12 +685,12 @@ 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=392)
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=16)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=392)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -883,194 +710,65 @@ 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) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[2304];
+extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[1];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 16)] = (((((9 <= ((((int)threadIdx.x) * 16) % 81)) && (((((int)threadIdx.x) * 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 16) / 81) * 49)) + ((((((int)threadIdx.x) * 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1)] = (((((9 <= (((((int)threadIdx.x) * 16) + 1) % 81)) && ((((((int)threadIdx.x) * 16) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 2)] = (((((9 <= (((((int)threadIdx.x) * 16) + 2) % 81)) && ((((((int)threadIdx.x) * 16) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 2) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 3)] = (((((9 <= (((((int)threadIdx.x) * 16) + 3) % 81)) && ((((((int)threadIdx.x) * 16) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 3) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 3) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 4)] = (((((9 <= (((((int)threadIdx.x) * 16) + 4) % 81)) && ((((((int)threadIdx.x) * 16) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 4) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 5)] = (((((9 <= (((((int)threadIdx.x) * 16) + 5) % 81)) && ((((((int)threadIdx.x) * 16) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 5) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 6)] = (((((9 <= (((((int)threadIdx.x) * 16) + 6) % 81)) && ((((((int)threadIdx.x) * 16) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 6) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 7)] = (((((9 <= (((((int)threadIdx.x) * 16) + 7) % 81)) && ((((((int)threadIdx.x) * 16) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 7) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 8)] = (((((9 <= (((((int)threadIdx.x) * 16) + 8) % 81)) && ((((((int)threadIdx.x) * 16) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 8) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 9) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 10)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 10) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 11)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 11) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 12)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 12) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 13)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 13) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 14)] = (((((9 <= (((((int)threadIdx.x) * 16) + 14) % 81)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 14) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 15)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 15) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 896)] = (((((9 <= (((((int)threadIdx.x) * 16) + 5) % 81)) && ((((((int)threadIdx.x) * 16) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 896) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 897)] = (((((9 <= (((((int)threadIdx.x) * 16) + 6) % 81)) && ((((((int)threadIdx.x) * 16) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 897) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 898)] = (((((9 <= (((((int)threadIdx.x) * 16) + 7) % 81)) && ((((((int)threadIdx.x) * 16) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 898) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 899)] = (((((9 <= (((((int)threadIdx.x) * 16) + 8) % 81)) && ((((((int)threadIdx.x) * 16) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 899) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 900)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 900) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 901)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 901) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 902)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 902) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 903)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 903) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 904)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 904) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 905)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 896) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 905) / 81) * 49)) + ((((((((int)threadIdx.x) * 16) + 896) / 9) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8 [...]
- pad_temp_shared[((((int)threadIdx.x) * 16) + 906)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 906) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 907)] = (((((9 <= (((((int)threadIdx.x) * 16) + 16) % 81)) && ((((((int)threadIdx.x) * 16) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 907) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 908)] = (((((9 <= (((((int)threadIdx.x) * 16) + 17) % 81)) && ((((((int)threadIdx.x) * 16) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 908) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 17) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 909)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 2) % 9)) && ((((((int)threadIdx.x) * 16) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 909) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 910)] = (((((9 <= (((((int)threadIdx.x) * 16) + 19) % 81)) && ((((((int)threadIdx.x) * 16) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 910) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 19) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 911)] = (((((9 <= (((((int)threadIdx.x) * 16) + 20) % 81)) && ((((((int)threadIdx.x) * 16) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 911) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 20) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1792)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1792) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1793)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1793) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1794)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1794) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1795)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1795) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1796)] = (((((9 <= (((((int)threadIdx.x) * 16) + 14) % 81)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1796) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1797)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1797) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1798)] = (((((9 <= (((((int)threadIdx.x) * 16) + 16) % 81)) && ((((((int)threadIdx.x) * 16) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1798) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 120) {
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1799)] = (((((9 <= (((((int)threadIdx.x) * 16) + 17) % 81)) && ((((((int)threadIdx.x) * 16) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1799) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 17) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1800)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 2) % 9)) && ((((((int)threadIdx.x) * 16) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1800) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1801)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 1792) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1801) / 81) * 49)) + ((((((((int)threadIdx.x) * 16) + 1792) / 9) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9 [...]
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1802)] = (((((9 <= (((((int)threadIdx.x) * 16) + 20) % 81)) && ((((((int)threadIdx.x) * 16) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1802) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 20) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1803)] = (((((9 <= (((((int)threadIdx.x) * 16) + 21) % 81)) && ((((((int)threadIdx.x) * 16) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1803) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 21) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1804)] = (((((9 <= (((((int)threadIdx.x) * 16) + 22) % 81)) && ((((((int)threadIdx.x) * 16) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1804) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 22) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1805)] = (((((9 <= (((((int)threadIdx.x) * 16) + 23) % 81)) && ((((((int)threadIdx.x) * 16) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1805) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 23) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1806)] = (((((9 <= (((((int)threadIdx.x) * 16) + 24) % 81)) && ((((((int)threadIdx.x) * 16) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1806) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 24) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1807)] = (((((9 <= (((((int)threadIdx.x) * 16) + 25) % 81)) && ((((((int)threadIdx.x) * 16) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1807) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 25) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 168)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 224) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 104) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 504) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 216)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 616) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 672) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 728) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 152) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 208) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 840) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 88) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 896) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 952) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1008) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1064) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 200) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1120) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1232) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1288) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 136) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1344) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 192)];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1400) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 248) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1456) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1512) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1624) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 184) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1680) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1736) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1792) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1848) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 120)];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1904) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 232) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2072) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2128) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2184) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 168)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 2240) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 224) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 280) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 32256)];
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 368) {
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 100)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 92)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 101)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 93)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 102)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 94)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 103)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 95)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 104)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 96)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 105)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 18)) + rx_outer_inner) + 15)]));
- }
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 324) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 36)) + 35)]));
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- }
+ compute[((((int)blockIdx.x) * 392) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -1106,7 +804,7 @@ 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> ( 5 minutes 55.884 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 33.158 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 23bcdac66a..a23df31c5b 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ 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)
- 7.7943 7.7966 7.8039 7.7824 0.0089
+ 7.8856 7.8871 7.8880 7.8816 0.0028
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ 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 2.666 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.048 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 3247f836f1..5dab488cce 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ 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)
- 775.5632 776.7474 777.0366 772.9058 1.8828
+ 761.9076 760.6141 764.6064 760.5022 1.9089
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ 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 33.562 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.814 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index ac2a56af06..48efaef985 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,29 +632,79 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [4096], [])[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 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*4096) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 128) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_22] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_22]), 0f32)
+ }
}
}
}
@@ -692,7 +742,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.564 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.722 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 4a509496a2..490973e08f 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:27.503</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:27.597</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:27.468</p></td>
+<td><p>00:27.561</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index f4a4eec499..b7a6e76388 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,8 +567,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 90.32/90.32 result: MeasureResult(costs=(0.0025632497906976745,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.293156862258911, timestamp=1672786477.372566) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,484682
-No: 2 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -690,8 +689,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4270075
-No: 3 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6188525
+No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -813,8 +812,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2675170
-No: 4 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8648012
+No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -936,9 +935,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4867909
-No: 5 GFLOPS: 7.29/90.32 result: MeasureResult(costs=(0.031743408,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8351917266845703, timestamp=1672786483.410508) [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3992223
-No: 6 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2499392
+No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1060,8 +1058,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 1]), ('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, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10258171
-No: 7 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8564334
+No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1183,8 +1181,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7930421
-No: 8 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1776587
+No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1306,8 +1304,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3519497
-No: 9 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9355026
+No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1429,8 +1427,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,191651
-No: 10 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3769498
+No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1552,8 +1550,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5379679
-No: 11 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6404388
+No: 9 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1675,8 +1673,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10014888
-No: 12 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1101238
+No: 10 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1798,8 +1796,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9071960
-No: 13 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3113668
+No: 11 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1921,8 +1919,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1329966
-No: 14 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2115181
+No: 12 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2044,8 +2042,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6882857
-No: 15 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6878598
+No: 13 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2167,9 +2165,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,700250
-No: 16 GFLOPS: 44.75/90.32 result: MeasureResult(costs=(0.00517342344,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.082315444946289, timestamp=1672786486.8927758) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7821809
-No: 17 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1485535
+No: 14 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2291,8 +2288,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3823609
-No: 18 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1518738
+No: 15 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2414,8 +2411,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4345966
-No: 19 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1638603
+No: 16 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2537,8 +2534,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8284252
-No: 20 GFLOPS: 0.00/90.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2766897
+No: 17 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2660,7 +2657,254 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4736783
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1149175
+No: 18 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:388
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:374
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:269
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:388
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:374
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:269
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2216305
+No: 19 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:388
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:374
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:269
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:388
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:374
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:269
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1693
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,387066
+No: 20 GFLOPS: 109.33/109.33 result: MeasureResult(costs=(0.002117441714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.47225284576416, timestamp=1672790261.0809987) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7376821
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2699,9 +2943,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,484682
+[('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7376821
Finish loading 20 records
-Time cost of this operator: 0.002954
+Time cost of this operator: 0.002111
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 07030b6013..fb90f486e4 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -598,10 +598,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.3 98.728 (1, 2, 10, 10, 3) 2 1 [312.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.039 0.961 (1, 6, 10, 10) 1 1 [3.039]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.985 0.312 (1, 1, 10, 10, 3) 1 1 [0.985]
-Total_time - 316.325 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 317.2 98.75 (1, 2, 10, 10, 3) 2 1 [317.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.026 0.942 (1, 6, 10, 10) 1 1 [3.026]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.99 0.308 (1, 1, 10, 10, 3) 1 1 [0.99]
+Total_time - 321.215 - - - - -
</pre></div>
</div>
</div>
@@ -653,10 +653,10 @@ 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 Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.8 97.574 (1, 6, 10, 10, 1) 2 1 [104.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.754 1.633 (1, 6, 10, 10) 1 1 [1.754]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.852 0.794 (1, 3, 10, 10, 1) 1 1 [0.852]
-Total_time - 107.406 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.509 (1, 6, 10, 10, 1) 2 1 [102.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.783 1.693 (1, 6, 10, 10) 1 1 [1.783]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.798 (1, 3, 10, 10, 1) 1 1 [0.84]
+Total_time - 105.323 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 3fd6803b70..7b8cc18b62 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,7 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 60.2MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 61.2MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -564,7 +564,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.369 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.583 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index c4f2e3e49d..5f593cc0cd 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmputeaywft/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpefiaqggl/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmputeaywft/images/target contains 8144 images
-/tmp/tmputeaywft/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpefiaqggl/images/target contains 8144 images
+/tmp/tmpefiaqggl/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2162 - accuracy: 0.9222 - val_loss: 0.1380 - val_accuracy: 0.9558 - 47s/epoch - 145ms/step
+328/328 - 48s - loss: 0.2220 - accuracy: 0.9225 - val_loss: 0.1097 - val_accuracy: 0.9619 - 48s/epoch - 145ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0950 - accuracy: 0.9656 - val_loss: 0.1047 - val_accuracy: 0.9653 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0941 - accuracy: 0.9638 - val_loss: 0.1063 - val_accuracy: 0.9656 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0635 - accuracy: 0.9753 - val_loss: 0.1158 - val_accuracy: 0.9660 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0631 - accuracy: 0.9755 - val_loss: 0.0962 - val_accuracy: 0.9702 - 44s/epoch - 133ms/step
-<keras.callbacks.History object at 0x7f4c62660550>
+<keras.callbacks.History object at 0x7f28d4a7a290>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 26.200 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 36.821 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index b87f2868be..1b579d5606 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:34.499</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:48.464</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:26.200</p></td>
+<td><p>04:36.821</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:04.369</p></td>
+<td><p>01:05.583</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:51.975</p></td>
+<td><p>00:53.956</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.093</p></td>
+<td><p>00:08.085</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.860</p></td>
+<td><p>00:04.017</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index eab8577858..045487fd8e 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.234</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:46.237</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.993</p></td>
+<td><p>00:34.297</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.563</p></td>
+<td><p>00:10.359</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.671</p></td>
+<td><p>00:01.574</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 978f86f948..a517fdb7ea 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f4bff34f440>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f28e0567dd0>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 602cbbf882..f96a3df218 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.484</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.939</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.919</p></td>
+<td><p>00:04.352</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.178</p></td>
+<td><p>00:01.183</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.592</p></td>
+<td><p>00:00.598</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.573</p></td>
+<td><p>00:00.581</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.118</p></td>
+<td><p>00:00.119</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -373,11 +373,11 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.030</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.024</p></td>
+<td><p>00:00.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index fd0ea2e78a..bd9ff55c8b 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjhc189pk/input0.cc'\nsource_filename = \"/tmp/tmpjhc189pk/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpy2zohiqq/input0.cc'\nsource_filename = \"/tmp/tmpy2zohiqq/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 1ef28de467..23d2181e9d 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,7 +229,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/doxygen/ir_2attrs_8h_source.html b/docs/reference/api/doxygen/ir_2attrs_8h_source.html
index b60fb90b16..7cdf34b857 100644
--- a/docs/reference/api/doxygen/ir_2attrs_8h_source.html
+++ b/docs/reference/api/doxygen/ir_2attrs_8h_source.html
@@ -154,7 +154,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1detail_1_1AttrsSHashVisitor_html"><div class="ttname"><a href="classtvm_1_1detail_1_1AttrsSHashVisitor.html">tvm::detail::AttrsSHashVisitor</a></div><div class="ttdef"><b>Definition:</b> attrs.h:487</div></div>
<div class="ttc" id="structtvm_1_1detail_1_1AttrTriggerNonDefaultEntry_html_ae3ca1012c8502b2d3132cc81530c6c0e"><div class="ttname"><a href="structtvm_1_1detail_1_1AttrTriggerNonDefaultEntry.html#ae3ca1012c8502b2d3132cc81530c6c0e">tvm::detail::AttrTriggerNonDefaultEntry::~AttrTriggerNonDefaultEntry</a></div><div class="ttdeci">~AttrTriggerNonDefaultEntry() DMLC_THROW_EXCEPTION</div><div class="ttdef"><b>Definition:</b> attrs.h:792</div></div>
<div class="ttc" id="classtvm_1_1detail_1_1AttrExistVisitor_html_a42cfd0949c298dea06fb2c4fb39e188d"><div class="ttname"><a href="classtvm_1_1detail_1_1AttrExistVisitor.html#a42cfd0949c298dea06fb2c4fb39e188d">tvm::detail::AttrExistVisitor::key_</a></div><div class="ttdeci">std::string key_</div><div class="ttdef"><b>Definition:</b> attrs.h:774</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1String_html_a2ee7733b1c8092383ffab8c67bf8cb20"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html#a2ee7733b1c8092383ffab8c67bf8cb20">tvm::runtime::String::CanConvertFrom</a></div><div class="ttdeci">static bool CanConvertFrom(const TVMArgValue &val)</div><div class="ttdoc">Check if a TVMArgValue can be converted to String, i.e. it can be std::string or String. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1972</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1String_html_a2ee7733b1c8092383ffab8c67bf8cb20"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html#a2ee7733b1c8092383ffab8c67bf8cb20">tvm::runtime::String::CanConvertFrom</a></div><div class="ttdeci">static bool CanConvertFrom(const TVMArgValue &val)</div><div class="ttdoc">Check if a TVMArgValue can be converted to String, i.e. it can be std::string or String. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1977</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
<div class="ttc" id="namespacetvm_html_a28c693333c2b15702b1a9a57dec0fbf5"><div class="ttname"><a href="namespacetvm.html#a28c693333c2b15702b1a9a57dec0fbf5">tvm::NullValue< DataType ></a></div><div class="ttdeci">DataType NullValue< DataType >()</div><div class="ttdef"><b>Definition:</b> attrs.h:90</div></div>
<div class="ttc" id="object_8h_html_af8330e3864503fb7c4133ae4d48fe4a2"><div class="ttname"><a href="object_8h.html#af8330e3864503fb7c4133ae4d48fe4a2">TVM_DEFINE_OBJECT_REF_COW_METHOD</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_COW_METHOD(ObjectName)</div><div class="ttdoc">Define CopyOnWrite function in an ObjectRef. </div><div class="ttdef"><b>Definition:</b> object.h:785</div></div>
diff --git a/docs/reference/api/doxygen/packed__func_8h_source.html b/docs/reference/api/doxygen/packed__func_8h_source.html
index 1287a9bbc6..9b692156db 100644
--- a/docs/reference/api/doxygen/packed__func_8h_source.html
+++ b/docs/reference/api/doxygen/packed__func_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">packed_func.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="packed__func_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or mor [...]
+<a href="packed__func_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or mor [...]
<div class="ttc" id="namespacetvm_1_1runtime_html_a129050a60cebb0bbe18f96b41a36a948"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a129050a60cebb0bbe18f96b41a36a948">tvm::runtime::ArgTypeCode2Str</a></div><div class="ttdeci">const char * ArgTypeCode2Str(int type_code)</div><div class="ttdoc">Convert argument type code to string. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1225</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMArgs_html_afec79c909bdf103a01cdb4732c0afdf3"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMArgs.html#afec79c909bdf103a01cdb4732c0afdf3">tvm::runtime::TVMArgs::num_args</a></div><div class="ttdeci">int num_args</div><div class="ttdef"><b>Definition:</b> packed_func.h:395</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMArgValue_html_a987b2fb283cea5484d4655e3f711c046"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMArgValue.html#a987b2fb283cea5484d4655e3f711c046">tvm::runtime::TVMArgValue::TVMArgValue</a></div><div class="ttdeci">TVMArgValue()</div><div class="ttdoc">default constructor </div><div class="ttdef"><b>Definition:</b> packed_func.h:649</div></div>
@@ -74,7 +74,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1TVMRetValue_html_a952f62623ec147f366363b664d749566"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMRetValue.html#a952f62623ec147f366363b664d749566">tvm::runtime::TVMRetValue::operator=</a></div><div class="ttdeci">TVMRetValue & operator=(std::string value)</div><div class="ttdef"><b>Definition:</b> packed_func.h:900</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ArrayNode_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ArrayNode.html">tvm::runtime::ArrayNode</a></div><div class="ttdoc">array node content in array </div><div class="ttdef"><b>Definition:</b> array.h:40</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMRetValue_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMRetValue.html">tvm::runtime::TVMRetValue</a></div><div class="ttdoc">Return Value container, Unlike TVMArgValue, which only holds reference and do not delete the underlyi...</div><div class="ttdef"><b>Definition:</b> packed_func.h:799</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1Module_html_a1233f7b896bb299ef07f9e41a4ffdc17"><div class="ttname"><a href="classtvm_1_1runtime_1_1Module.html#a1233f7b896bb299ef07f9e41a4ffdc17">tvm::runtime::Module::GetFunction</a></div><div class="ttdeci">PackedFunc GetFunction(const std::string &name, bool query_imports=false)</div><div class="ttdoc">Get packed function from current module by name. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1936</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1Module_html_a1233f7b896bb299ef07f9e41a4ffdc17"><div class="ttname"><a href="classtvm_1_1runtime_1_1Module.html#a1233f7b896bb299ef07f9e41a4ffdc17">tvm::runtime::Module::GetFunction</a></div><div class="ttdeci">PackedFunc GetFunction(const std::string &name, bool query_imports=false)</div><div class="ttdoc">Get packed function from current module by name. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1941</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1NDArray_html_ade0e2757904f4f5ba5c667ae01793a47"><div class="ttname"><a href="classtvm_1_1runtime_1_1NDArray.html#ade0e2757904f4f5ba5c667ae01793a47">tvm::runtime::NDArray::FFIDecRef</a></div><div class="ttdeci">static void FFIDecRef(TVMArrayHandle handle)</div><div class="ttdoc">DecRef resource managed by an FFI array handle. </div><div class="ttdef"><b>Definition:</b> ndarray.h:438</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMRetValue_html_ae47baae854e2ff66d0ef87178727d8f4"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMRetValue.html#ae47baae854e2ff66d0ef87178727d8f4">tvm::runtime::TVMRetValue::operator=</a></div><div class="ttdeci">TVMRetValue & operator=(TVMMovableArgValue_ &&other)</div><div class="ttdef"><b>Definition:</b> packed_func.h:940</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMArgsSetter_html_a4c6dffcee3ea29b0b5862f1cc42c5c1c"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMArgsSetter.html#a4c6dffcee3ea29b0b5862f1cc42c5c1c">tvm::runtime::TVMArgsSetter::operator()</a></div><div class="ttdeci">TVM_ALWAYS_INLINE void operator()(size_t i, TObjectRef &&value) const</div><div class="ttdef"><b>Definition:</b> packed_func.h:1595</div></div>
@@ -134,14 +134,14 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1TVMMovableArgValue___html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMMovableArgValue__.html">tvm::runtime::TVMMovableArgValue_</a></div><div class="ttdoc">Internal auxiliary struct for TypedPackedFunc to indicate a movable argument. </div><div class="ttdef"><b>Definition:</b> packed_func.h:709</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1ObjectTypeChecker_3_01Map_3_01K_00_01V_01_4_01_4_html_a66cc223f8e80086a6396540546b07eed"><div class="ttname"><a href="structtvm_1_1runtime_1_1ObjectTypeChecker_3_01Map_3_01K_00_01V_01_4_01_4.html#a66cc223f8e80086a6396540546b07eed">tvm::runtime::ObjectTypeChecker< Map< K, V > >::Check</a></div><div class="ttdeci">static bool Check(const Object *ptr)</div><div class="ttdef"><b>Definition:</b> packed_func.h:521</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMArgsSetter_html_a533c034c471f3c09341dcfbfcbb20d9a"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMArgsSetter.html#a533c034c471f3c09341dcfbfcbb20d9a">tvm::runtime::TVMArgsSetter::operator()</a></div><div class="ttdeci">TVM_ALWAYS_INLINE void operator()(size_t i, T value) const</div><div class="ttdef"><b>Definition:</b> packed_func.h:1518</div></div>
-<div class="ttc" id="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_01Optional_3_01T_01_4_01_4_html_a621ed59fef92109e666150923621379c"><div class="ttname"><a href="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_01Optional_3_01T_01_4_01_4.html#a621ed59fef92109e666150923621379c">tvm::runtime::PackedFuncValueConverter< Optional< T > >::From</a></div><div class="ttdeci">static Optional< T > From(const TVMRetValue &val)</div><div class="ttdef"><b>Definition:</b> [...]
+<div class="ttc" id="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_01Optional_3_01T_01_4_01_4_html_a621ed59fef92109e666150923621379c"><div class="ttname"><a href="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_01Optional_3_01T_01_4_01_4.html#a621ed59fef92109e666150923621379c">tvm::runtime::PackedFuncValueConverter< Optional< T > >::From</a></div><div class="ttdeci">static Optional< T > From(const TVMRetValue &val)</div><div class="ttdef"><b>Definition:</b> [...]
<div class="ttc" id="ndarray_8h_html"><div class="ttname"><a href="ndarray_8h.html">ndarray.h</a></div><div class="ttdoc">A device-independent managed NDArray abstraction. </div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a277f104e659f71cd8885744700016341"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a277f104e659f71cd8885744700016341">tvm::runtime::String2DLDataType</a></div><div class="ttdeci">DLDataType String2DLDataType(std::string s)</div><div class="ttdoc">convert a string to TVM type. </div><div class="ttdef"><b>Definition:</b> data_type.h:348</div></div>
-<div class="ttc" id="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_1_1tvm_1_1runtime_1_1String_01_4_html_a9ac48d52f86dc3718590acc119e88741"><div class="ttname"><a href="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_1_1tvm_1_1runtime_1_1String_01_4.html#a9ac48d52f86dc3718590acc119e88741">tvm::runtime::PackedFuncValueConverter<::tvm::runtime::String >::From</a></div><div class="ttdeci">static String From(const TVMRetValue &val)</div><div class="ttdef"><b>Definition:</b> [...]
+<div class="ttc" id="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_1_1tvm_1_1runtime_1_1String_01_4_html_a9ac48d52f86dc3718590acc119e88741"><div class="ttname"><a href="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_1_1tvm_1_1runtime_1_1String_01_4.html#a9ac48d52f86dc3718590acc119e88741">tvm::runtime::PackedFuncValueConverter<::tvm::runtime::String >::From</a></div><div class="ttdeci">static String From(const TVMRetValue &val)</div><div class="ttdef"><b>Definition:</b> [...]
<div class="ttc" id="classtvm_1_1runtime_1_1NDArray_html_ab76ba9c638e1d6db8d6f0ba8c4d38670"><div class="ttname"><a href="classtvm_1_1runtime_1_1NDArray.html#ab76ba9c638e1d6db8d6f0ba8c4d38670">tvm::runtime::NDArray::FFIDataFromHandle</a></div><div class="ttdeci">static ObjectPtr< Object > FFIDataFromHandle(TVMArrayHandle handle)</div><div class="ttdoc">Construct NDArray&#39;s Data field from array handle in FFI. </div><div class="ttdef"><b>Definition:</b> ndarray.h:425</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1ObjectTypeChecker_html"><div class="ttname"><a href="structtvm_1_1runtime_1_1ObjectTypeChecker.html">tvm::runtime::ObjectTypeChecker</a></div><div class="ttdoc">Type traits for runtime type check during FFI conversion. </div><div class="ttdef"><b>Definition:</b> packed_func.h:430</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMPODValue___html_a67fdc41da2d772f61a924b8fa2d820e5"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMPODValue__.html#a67fdc41da2d772f61a924b8fa2d820e5">tvm::runtime::TVMPODValue_::IsObjectRef</a></div><div class="ttdeci">bool IsObjectRef() const</div><div class="ttdef"><b>Definition:</b> packed_func.h:1791</div></div>
-<div class="ttc" id="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_01Optional_3_01T_01_4_01_4_html_a6748e04a16945df4c15edb53d0aaba70"><div class="ttname"><a href="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_01Optional_3_01T_01_4_01_4.html#a6748e04a16945df4c15edb53d0aaba70">tvm::runtime::PackedFuncValueConverter< Optional< T > >::From</a></div><div class="ttdeci">static Optional< T > From(const TVMArgValue &val)</div><div class="ttdef"><b>Definition:</b> [...]
+<div class="ttc" id="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_01Optional_3_01T_01_4_01_4_html_a6748e04a16945df4c15edb53d0aaba70"><div class="ttname"><a href="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_01Optional_3_01T_01_4_01_4.html#a6748e04a16945df4c15edb53d0aaba70">tvm::runtime::PackedFuncValueConverter< Optional< T > >::From</a></div><div class="ttdeci">static Optional< T > From(const TVMArgValue &val)</div><div class="ttdef"><b>Definition:</b> [...]
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html">tvm::runtime::DataType</a></div><div class="ttdoc">Runtime primitive data type. </div><div class="ttdef"><b>Definition:</b> data_type.h:41</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_a17d8d5ad92691f9e18e3e0ae8ef69e4f"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#a17d8d5ad92691f9e18e3e0ae8ef69e4f">tvm::runtime::ObjectRef::defined</a></div><div class="ttdeci">bool defined() const</div><div class="ttdef"><b>Definition:</b> object.h:544</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMArgsSetter_html_a784a2e0f1412187befbacf0b23dbcd12"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMArgsSetter.html#a784a2e0f1412187befbacf0b23dbcd12">tvm::runtime::TVMArgsSetter::operator()</a></div><div class="ttdeci">TVM_ALWAYS_INLINE void operator()(size_t i, Device value) const</div><div class="ttdef"><b>Definition:</b> packed_func.h:1547</div></div>
@@ -189,7 +189,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1PackedFuncObj_html_a2b8fa6433efeccb77c9a1675ee7a3223"><div class="ttname"><a href="classtvm_1_1runtime_1_1PackedFuncObj.html#a2b8fa6433efeccb77c9a1675ee7a3223">tvm::runtime::PackedFuncObj::TVM_DECLARE_FINAL_OBJECT_INFO</a></div><div class="ttdeci">TVM_DECLARE_FINAL_OBJECT_INFO(PackedFuncObj, Object)</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1PackedFuncSubObj_html_a969aa766a25d7e9091e08b3a8e1ea974"><div class="ttname"><a href="classtvm_1_1runtime_1_1PackedFuncSubObj.html#a969aa766a25d7e9091e08b3a8e1ea974">tvm::runtime::PackedFuncSubObj::callable_</a></div><div class="ttdeci">TStorage callable_</div><div class="ttdoc">Type-erased filed for storing callable object. </div><div class="ttdef"><b>Definition:</b> packed_func.h:127</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1ObjectTypeChecker_html_aebb30723fbc8a9530855dfd4f6185e89"><div class="ttname"><a href="structtvm_1_1runtime_1_1ObjectTypeChecker.html#aebb30723fbc8a9530855dfd4f6185e89">tvm::runtime::ObjectTypeChecker::CheckAndGetMismatch</a></div><div class="ttdeci">static Optional< String > CheckAndGetMismatch(const Object *ptr)</div><div class="ttdoc">Check if an object matches the template type and return the mismatched type if it exists...</div><div [...]
-<div class="ttc" id="classtvm_1_1runtime_1_1String_html_a2ee7733b1c8092383ffab8c67bf8cb20"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html#a2ee7733b1c8092383ffab8c67bf8cb20">tvm::runtime::String::CanConvertFrom</a></div><div class="ttdeci">static bool CanConvertFrom(const TVMArgValue &val)</div><div class="ttdoc">Check if a TVMArgValue can be converted to String, i.e. it can be std::string or String. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1972</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1String_html_a2ee7733b1c8092383ffab8c67bf8cb20"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html#a2ee7733b1c8092383ffab8c67bf8cb20">tvm::runtime::String::CanConvertFrom</a></div><div class="ttdeci">static bool CanConvertFrom(const TVMArgValue &val)</div><div class="ttdoc">Check if a TVMArgValue can be converted to String, i.e. it can be std::string or String. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1977</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ModuleNode_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ModuleNode.html">tvm::runtime::ModuleNode</a></div><div class="ttdoc">Base container of module. </div><div class="ttdef"><b>Definition:</b> module.h:113</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1PackedFuncObj_html_ae5f18a03762f4e3e347b624140774855"><div class="ttname"><a href="classtvm_1_1runtime_1_1PackedFuncObj.html#ae5f18a03762f4e3e347b624140774855">tvm::runtime::PackedFuncObj::CallPacked</a></div><div class="ttdeci">TVM_ALWAYS_INLINE void CallPacked(TVMArgs args, TVMRetValue *rv) const</div><div class="ttdoc">Call the function in packed format. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1216</div></div>
@@ -211,7 +211,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html_a817ba6c23b7ee1821c48a75edf255a30"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object::TypeIndex2Key</a></div><div class="ttdeci">static std::string TypeIndex2Key(uint32_t tindex)</div><div class="ttdoc">Get the type key of the corresponding index from runtime. </div></div>
<div class="ttc" id="namespacetvm_html_a0da40d3e210aa3b38a17982a7b7866b8"><div class="ttname"><a href="namespacetvm.html#a0da40d3e210aa3b38a17982a7b7866b8">tvm::ret</a></div><div class="ttdeci">PrimExpr ret(PrimExpr value, Span span=Span())</div><div class="ttdoc">Return the value. </div></div>
<div class="ttc" id="map_8h_html"><div class="ttname"><a href="map_8h.html">map.h</a></div><div class="ttdoc">Runtime Map container types. </div></div>
-<div class="ttc" id="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_1_1tvm_1_1runtime_1_1String_01_4_html_a1d57124f26aeed2583d3ae24226d89c7"><div class="ttname"><a href="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_1_1tvm_1_1runtime_1_1String_01_4.html#a1d57124f26aeed2583d3ae24226d89c7">tvm::runtime::PackedFuncValueConverter<::tvm::runtime::String >::From</a></div><div class="ttdeci">static String From(const TVMArgValue &val)</div><div class="ttdef"><b>Definition:</b> [...]
+<div class="ttc" id="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_1_1tvm_1_1runtime_1_1String_01_4_html_a1d57124f26aeed2583d3ae24226d89c7"><div class="ttname"><a href="structtvm_1_1runtime_1_1PackedFuncValueConverter_3_1_1tvm_1_1runtime_1_1String_01_4.html#a1d57124f26aeed2583d3ae24226d89c7">tvm::runtime::PackedFuncValueConverter<::tvm::runtime::String >::From</a></div><div class="ttdeci">static String From(const TVMArgValue &val)</div><div class="ttdef"><b>Definition:</b> [...]
<div class="ttc" id="structtvm_1_1runtime_1_1ObjectTypeChecker_3_01Map_3_01K_00_01V_01_4_01_4_html_a9cb994fc6604ad2c287d9e824e67d2e2"><div class="ttname"><a href="structtvm_1_1runtime_1_1ObjectTypeChecker_3_01Map_3_01K_00_01V_01_4_01_4.html#a9cb994fc6604ad2c287d9e824e67d2e2">tvm::runtime::ObjectTypeChecker< Map< K, V > >::TypeName</a></div><div class="ttdeci">static std::string TypeName()</div><div class="ttdef"><b>Definition:</b> packed_func.h:531</div></div>
<div class="ttc" id="c__runtime__api_8h_html_a190e81769e805cca153514137a66e793ada22c3d9c62fa8f40d46e80ce83b96a1"><div class="ttname"><a href="c__runtime__api_8h.html#a190e81769e805cca153514137a66e793ada22c3d9c62fa8f40d46e80ce83b96a1">kTVMNullptr</a></div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:171</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMPODValue___html_aefca71073146f4be36d6a4a0de33d6e0"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMPODValue__.html#aefca71073146f4be36d6a4a0de33d6e0">tvm::runtime::TVMPODValue_::type_code</a></div><div class="ttdeci">int type_code() const</div><div class="ttdef"><b>Definition:</b> packed_func.h:610</div></div>
diff --git a/docs/reference/api/doxygen/runtime_2module_8h_source.html b/docs/reference/api/doxygen/runtime_2module_8h_source.html
index dbb08ab169..23b5a40822 100644
--- a/docs/reference/api/doxygen/runtime_2module_8h_source.html
+++ b/docs/reference/api/doxygen/runtime_2module_8h_source.html
@@ -68,7 +68,7 @@ $(function() {
<div class="contents">
<a href="runtime_2module_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
<div class="ttc" id="namespacetvm_1_1runtime_1_1symbol_html_aaad9cf8f51a55b2ec5b19854d692bd21"><div class="ttname"><a href="namespacetvm_1_1runtime_1_1symbol.html#aaad9cf8f51a55b2ec5b19854d692bd21">tvm::runtime::symbol::tvm_set_device</a></div><div class="ttdeci">constexpr const char * tvm_set_device</div><div class="ttdoc">global function to set device </div><div class="ttdef"><b>Definition:</b> module.h:259</div></div>
-<div class="ttc" id="classtvm_1_1runtime_1_1Module_html_a1233f7b896bb299ef07f9e41a4ffdc17"><div class="ttname"><a href="classtvm_1_1runtime_1_1Module.html#a1233f7b896bb299ef07f9e41a4ffdc17">tvm::runtime::Module::GetFunction</a></div><div class="ttdeci">PackedFunc GetFunction(const std::string &name, bool query_imports=false)</div><div class="ttdoc">Get packed function from current module by name. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1936</div></div>
+<div class="ttc" id="classtvm_1_1runtime_1_1Module_html_a1233f7b896bb299ef07f9e41a4ffdc17"><div class="ttname"><a href="classtvm_1_1runtime_1_1Module.html#a1233f7b896bb299ef07f9e41a4ffdc17">tvm::runtime::Module::GetFunction</a></div><div class="ttdeci">PackedFunc GetFunction(const std::string &name, bool query_imports=false)</div><div class="ttdoc">Get packed function from current module by name. </div><div class="ttdef"><b>Definition:</b> packed_func.h:1941</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Module_html_afb5a6c9b0e0a541245958456ebe39260"><div class="ttname"><a href="classtvm_1_1runtime_1_1Module.html#afb5a6c9b0e0a541245958456ebe39260">tvm::runtime::Module::Import</a></div><div class="ttdeci">void Import(Module other)</div><div class="ttdoc">Import another module into this module. </div><div class="ttdef"><b>Definition:</b> module.h:276</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectPtr_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectPtr.html">tvm::runtime::ObjectPtr</a></div><div class="ttdoc">A custom smart pointer for Object. </div><div class="ttdef"><b>Definition:</b> object.h:358</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1TypeIndex_html_aed93c7318efc8052201d4c404b21a40da8ce1dbb49ce074502049c6909061a2ae"><div class="ttname"><a href="structtvm_1_1runtime_1_1TypeIndex.html#aed93c7318efc8052201d4c404b21a40da8ce1dbb49ce074502049c6909061a2ae">tvm::runtime::TypeIndex::kRuntimeModule</a></div><div class="ttdoc">runtime::Module. </div><div class="ttdef"><b>Definition:</b> object.h:62</div></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 764d81a660..0f6f7be9f0 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 4bad921b62..bef5490154 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/e24d4fb78/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 109fdf8ed6..5beaff4321 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/e24d4fb78/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 75a65be8d6..44d52f0ae6 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/e24d4fb78/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 d78db5fbd8..d75f383969 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/e24d4fb78/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 724c46c9f3..286bae3b75 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/e24d4fb78/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 1568208911..96e3463105 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/e24d4fb78/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 30d47b8e13..3fd392f2af 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/e24d4fb78/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 77bd6e169c..c9527ec5b1 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/e24d4fb78/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/e24d4fb78/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 26b3ed7d58..d2371cb3da 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/e24d4fb78/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 b5ba643168..ed19fac585 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/e24d4fb78/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 6e7a537bbf..a0991b0883 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/e24d4fb78/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 b7ddf4bf27..169247cdb3 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/e24d4fb78/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 4f728673ba..6bcc51bd11 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/e24d4fb78/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 a6e9c76f84..14f9b696f6 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/e24d4fb78/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 97bd3b84fe..76f77f4cd9 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/e24d4fb78/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 9dc2795f5e..c216c641d1 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/e24d4fb78/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 3828c9b1e2..74717ee1b7 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/e24d4fb78/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 3d539fd40d..1453b0d721 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/e24d4fb78/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 cc886936c5..20165c293c 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/e24d4fb78/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 414be7423f..0538482a0c 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/e24d4fb78/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 38fee608a7..b5f7970390 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/e24d4fb78/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/e24d4fb78/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 857ebedffc..99911fdf66 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/e24d4fb78/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 fc4c4a070f..fdfa4a938f 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/e24d4fb78/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 fa882f9399..811516b6db 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/e24d4fb78/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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/e24d4fb78/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/45a8a44b8/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 8cd199a0be..9edd8c872c 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 4cd38e5830..0c6d9a9a8d 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:27.382</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:27.742</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:27.375</p></td>
+<td><p>00:27.735</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 42b564f980..e10e2c59e4 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ 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 30.65s!
+resnet18_v1 inference graph built in 31.01s!
</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 b716fdead3..b3cd883059 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 20.27s!
+yolov3-tiny inference graph built in 20.74s!
</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 3ab7fe9d29..55e37f2904 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:42.872</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:43.872</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:52.177</p></td>
+<td><p>00:52.829</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:50.695</p></td>
+<td><p>00:51.043</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 54ad7eac9a..1c14f26fe1 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.183</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.226</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.708</p></td>
+<td><p>00:02.748</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.475</p></td>
+<td><p>00:00.478</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 3047687357..f971a64d56 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.855</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.845</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.455</p></td>
+<td><p>00:00.448</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.400</p></td>
+<td><p>00:00.397</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index be78409926..faf088ea9b 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -577,7 +577,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.940 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 100.237 ms
</pre></div>
</div>
</div>
@@ -651,7 +651,7 @@ 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 13.124 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.424 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 2e3eea2333..6be9596aea 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 11.54/11.54 result: MeasureResult(costs=(0.0232534442,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6074883937835693, timestamp=1672785039.2747946) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
-No: 2 GFLOPS: 2.05/11.54 result: MeasureResult(costs=(0.1311131504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3415377140045166, timestamp=1672785042.39668) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
-No: 3 GFLOPS: 10.86/11.54 result: MeasureResult(costs=(0.0247229354,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6333410739898682, timestamp=1672785043.053513) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
-No: 4 GFLOPS: 1.77/11.54 result: MeasureResult(costs=(0.151981095,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.655801296234131, timestamp=1672785046.517171) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
-No: 5 GFLOPS: 12.66/12.66 result: MeasureResult(costs=(0.0212016438,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5941817760467529, timestamp=1672785047.2356257) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
-No: 6 GFLOPS: 12.90/12.90 result: MeasureResult(costs=(0.020816462799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5831103324890137, timestamp=1672785047.8258975) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
-No: 7 GFLOPS: 10.53/12.90 result: MeasureResult(costs=(0.0254842988,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6501202583312988, timestamp=1672785049.2774296) [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
-No: 8 GFLOPS: 1.55/12.90 result: MeasureResult(costs=(0.172636044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0099596977233887, timestamp=1672785052.2972908) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
-No: 9 GFLOPS: 1.22/12.90 result: MeasureResult(costs=(0.2202219296,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7197518348693848, timestamp=1672785056.1386836) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
-No: 10 GFLOPS: 1.17/12.90 result: MeasureResult(costs=(0.22848886680000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.859966993331909, timestamp=1672785060.0476418) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+No: 1 GFLOPS: 10.25/10.25 result: MeasureResult(costs=(0.026194271199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.664623498916626, timestamp=1672788792.4754536) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
+No: 2 GFLOPS: 1.08/10.25 result: MeasureResult(costs=(0.2496804558,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.244028806686401, timestamp=1672788796.7307754) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+No: 3 GFLOPS: 9.72/10.25 result: MeasureResult(costs=(0.027611750400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7044909000396729, timestamp=1672788798.2370958) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
+No: 4 GFLOPS: 12.18/12.18 result: MeasureResult(costs=(0.0220330818,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.570030689239502, timestamp=1672788799.6622183) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+No: 5 GFLOPS: 10.31/12.18 result: MeasureResult(costs=(0.0260387062,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.711327314376831, timestamp=1672788800.568145) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+No: 6 GFLOPS: 2.43/12.18 result: MeasureResult(costs=(0.110456584,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.003021717071533, timestamp=1672788803.3919518) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+No: 7 GFLOPS: 9.82/12.18 result: MeasureResult(costs=(0.027326444999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8071770668029785, timestamp=1672788804.0915456) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
+No: 8 GFLOPS: 2.75/12.18 result: MeasureResult(costs=(0.0977106252,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8109846115112305, timestamp=1672788805.9069953) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 9 GFLOPS: 8.28/12.18 result: MeasureResult(costs=(0.032406979,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7195665836334229, timestamp=1672788806.7501853) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+No: 10 GFLOPS: 0.89/12.18 result: MeasureResult(costs=(0.30044604639999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.021171808242798, timestamp=1672788811.8149707) [('tile_y', [-1, 128]), ('tile_x', [-1, 2])],None,17
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index a03132f76d..f33af515f2 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 513.194206589999, 'median': 512.949942749998, 'std': 2.1665419819072995}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 523.192951289999, 'median': 523.8391569499925, 'std': 2.481909805515635}
</pre></div>
</div>
</div>
@@ -712,177 +712,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 12.60/ 22.54 GFLOPS | Progress: (4/20) | 6.78 s
-[Task 1/25] Current/Best: 19.11/ 22.54 GFLOPS | Progress: (8/20) | 10.41 s
-[Task 1/25] Current/Best: 12.50/ 22.54 GFLOPS | Progress: (12/20) | 12.55 s
-[Task 1/25] Current/Best: 13.47/ 22.54 GFLOPS | Progress: (16/20) | 17.50 s
-[Task 1/25] Current/Best: 19.32/ 23.79 GFLOPS | Progress: (20/20) | 19.49 s Done.
+[Task 1/25] Current/Best: 12.03/ 12.28 GFLOPS | Progress: (4/20) | 9.30 s
+[Task 1/25] Current/Best: 16.55/ 16.55 GFLOPS | Progress: (8/20) | 12.52 s
+[Task 1/25] Current/Best: 12.73/ 16.55 GFLOPS | Progress: (12/20) | 15.04 s
+[Task 1/25] Current/Best: 7.03/ 16.79 GFLOPS | Progress: (16/20) | 17.97 s
+[Task 1/25] Current/Best: 12.52/ 22.78 GFLOPS | Progress: (20/20) | 20.86 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 6.51/ 19.48 GFLOPS | Progress: (4/20) | 3.21 s
-[Task 2/25] Current/Best: 11.73/ 19.48 GFLOPS | Progress: (8/20) | 5.11 s
-[Task 2/25] Current/Best: 7.63/ 19.48 GFLOPS | Progress: (12/20) | 8.16 s
-[Task 2/25] Current/Best: 16.81/ 19.48 GFLOPS | Progress: (16/20) | 9.92 s
-[Task 2/25] Current/Best: 7.18/ 19.48 GFLOPS | Progress: (20/20) | 11.69 s Done.
+[Task 2/25] Current/Best: 11.84/ 15.49 GFLOPS | Progress: (4/20) | 3.80 s
+[Task 2/25] Current/Best: 6.42/ 15.49 GFLOPS | Progress: (8/20) | 5.50 s
+[Task 2/25] Current/Best: 3.27/ 17.76 GFLOPS | Progress: (12/20) | 7.80 s
+[Task 2/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (16/20) | 9.17 s
+[Task 2/25] Current/Best: 3.66/ 21.00 GFLOPS | Progress: (20/20) | 10.56 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 12.38/ 14.37 GFLOPS | Progress: (4/20) | 4.92 s
-[Task 3/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (8/20) | 7.14 s
-[Task 3/25] Current/Best: 10.03/ 21.17 GFLOPS | Progress: (12/20) | 9.85 s
-[Task 3/25] Current/Best: 1.62/ 21.17 GFLOPS | Progress: (16/20) | 14.08 s
-[Task 3/25] Current/Best: 11.81/ 21.17 GFLOPS | Progress: (20/20) | 16.72 s Done.
+[Task 3/25] Current/Best: 15.65/ 16.92 GFLOPS | Progress: (4/20) | 4.71 s
+[Task 3/25] Current/Best: 19.85/ 19.91 GFLOPS | Progress: (8/20) | 7.06 s
+[Task 3/25] Current/Best: 10.07/ 19.91 GFLOPS | Progress: (12/20) | 9.46 s
+[Task 3/25] Current/Best: 14.77/ 19.91 GFLOPS | Progress: (16/20) | 11.97 s
+[Task 3/25] Current/Best: 18.14/ 20.00 GFLOPS | Progress: (20/20) | 14.03 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 11.79/ 17.55 GFLOPS | Progress: (4/20) | 3.95 s
-[Task 4/25] Current/Best: 8.24/ 17.55 GFLOPS | Progress: (8/20) | 6.32 s
-[Task 4/25] Current/Best: 15.77/ 21.58 GFLOPS | Progress: (12/20) | 12.19 s
-[Task 4/25] Current/Best: 16.53/ 21.58 GFLOPS | Progress: (16/20) | 17.13 s
-[Task 4/25] Current/Best: 13.25/ 21.58 GFLOPS | Progress: (20/20) | 21.79 s Done.
+[Task 4/25] Current/Best: 11.85/ 19.22 GFLOPS | Progress: (4/20) | 3.82 s
+[Task 4/25] Current/Best: 12.01/ 22.39 GFLOPS | Progress: (8/20) | 5.81 s
+[Task 4/25] Current/Best: 11.35/ 22.39 GFLOPS | Progress: (12/20) | 8.98 s
+[Task 4/25] Current/Best: 17.71/ 22.39 GFLOPS | Progress: (16/20) | 13.81 s
+[Task 4/25] Current/Best: 8.76/ 22.39 GFLOPS | Progress: (20/20) | 15.59 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 3.43/ 15.27 GFLOPS | Progress: (4/20) | 4.05 s
-[Task 5/25] Current/Best: 12.14/ 17.98 GFLOPS | Progress: (8/20) | 6.63 s
-[Task 5/25] Current/Best: 6.63/ 21.63 GFLOPS | Progress: (12/20) | 8.54 s
-[Task 5/25] Current/Best: 18.37/ 21.63 GFLOPS | Progress: (16/20) | 10.61 s
-[Task 5/25] Current/Best: 4.77/ 21.63 GFLOPS | Progress: (20/20) | 12.87 s Done.
+[Task 5/25] Current/Best: 11.48/ 13.08 GFLOPS | Progress: (4/20) | 4.59 s
+[Task 5/25] Current/Best: 9.86/ 13.08 GFLOPS | Progress: (8/20) | 7.03 s
+[Task 5/25] Current/Best: 13.06/ 13.08 GFLOPS | Progress: (12/20) | 9.17 s
+[Task 5/25] Current/Best: 9.34/ 13.28 GFLOPS | Progress: (16/20) | 11.44 s
+[Task 5/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (20/20) | 13.14 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 21.59/ 21.59 GFLOPS | Progress: (4/20) | 5.16 s
-[Task 6/25] Current/Best: 11.95/ 21.59 GFLOPS | Progress: (8/20) | 7.10 s
-[Task 6/25] Current/Best: 12.55/ 21.59 GFLOPS | Progress: (12/20) | 10.16 s
-[Task 6/25] Current/Best: 14.21/ 21.59 GFLOPS | Progress: (16/20) | 15.43 s
-[Task 6/25] Current/Best: 10.51/ 21.59 GFLOPS | Progress: (20/20) | 18.17 s Done.
+[Task 6/25] Current/Best: 4.43/ 15.78 GFLOPS | Progress: (4/20) | 4.41 s
+[Task 6/25] Current/Best: 11.42/ 15.78 GFLOPS | Progress: (8/20) | 7.30 s
+[Task 6/25] Current/Best: 13.08/ 15.78 GFLOPS | Progress: (12/20) | 10.02 s
+[Task 6/25] Current/Best: 10.38/ 16.67 GFLOPS | Progress: (16/20) | 12.45 s
+[Task 6/25] Current/Best: 9.43/ 16.67 GFLOPS | Progress: (20/20) | 16.29 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 6.77/ 17.89 GFLOPS | Progress: (4/20) | 4.74 s
-[Task 7/25] Current/Best: 9.20/ 17.89 GFLOPS | Progress: (8/20) | 6.92 s
-[Task 7/25] Current/Best: 14.81/ 17.89 GFLOPS | Progress: (12/20) | 8.96 s
-[Task 7/25] Current/Best: 17.47/ 17.89 GFLOPS | Progress: (16/20) | 11.99 s
-[Task 7/25] Current/Best: 16.21/ 17.89 GFLOPS | Progress: (20/20) | 14.54 s Done.
+[Task 7/25] Current/Best: 11.70/ 16.64 GFLOPS | Progress: (4/20) | 5.10 s
+[Task 7/25] Current/Best: 11.83/ 17.73 GFLOPS | Progress: (8/20) | 7.13 s
+[Task 7/25] Current/Best: 6.51/ 17.73 GFLOPS | Progress: (12/20) | 9.76 s
+[Task 7/25] Current/Best: 12.13/ 17.73 GFLOPS | Progress: (16/20) | 12.57 s
+[Task 7/25] Current/Best: 11.67/ 18.98 GFLOPS | Progress: (20/20) | 14.96 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 3.81/ 12.59 GFLOPS | Progress: (4/20) | 13.73 s
-[Task 8/25] Current/Best: 17.39/ 18.71 GFLOPS | Progress: (8/20) | 17.52 s
-[Task 8/25] Current/Best: 2.56/ 19.58 GFLOPS | Progress: (12/20) | 20.72 s
-[Task 8/25] Current/Best: 12.34/ 19.58 GFLOPS | Progress: (16/20) | 23.22 s
-[Task 8/25] Current/Best: 7.86/ 19.58 GFLOPS | Progress: (20/20) | 27.56 s
-[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 11.34/ 16.44 GFLOPS | Progress: (4/20) | 3.61 s
-[Task 9/25] Current/Best: 13.31/ 16.44 GFLOPS | Progress: (8/20) | 5.91 s
-[Task 9/25] Current/Best: 6.75/ 19.08 GFLOPS | Progress: (12/20) | 7.65 s
-[Task 9/25] Current/Best: 16.05/ 19.08 GFLOPS | Progress: (16/20) | 10.42 s
-[Task 9/25] Current/Best: 1.94/ 21.56 GFLOPS | Progress: (20/20) | 19.73 s Done.
+[Task 8/25] Current/Best: 4.73/ 21.57 GFLOPS | Progress: (4/20) | 4.77 s
+[Task 8/25] Current/Best: 14.19/ 21.57 GFLOPS | Progress: (8/20) | 7.48 s
+[Task 8/25] Current/Best: 4.02/ 21.57 GFLOPS | Progress: (12/20) | 11.02 s
+[Task 8/25] Current/Best: 2.82/ 21.57 GFLOPS | Progress: (16/20) | 15.35 s
+[Task 8/25] Current/Best: 9.92/ 21.57 GFLOPS | Progress: (20/20) | 17.70 s Done.
+[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 9/25] Current/Best: 7.05/ 14.10 GFLOPS | Progress: (4/20) | 7.40 s
+[Task 9/25] Current/Best: 15.14/ 16.38 GFLOPS | Progress: (8/20) | 9.45 s
+[Task 9/25] Current/Best: 12.33/ 17.20 GFLOPS | Progress: (12/20) | 17.49 s
+[Task 9/25] Current/Best: 12.02/ 18.21 GFLOPS | Progress: (16/20) | 19.71 s
+[Task 9/25] Current/Best: 10.56/ 18.21 GFLOPS | Progress: (20/20) | 30.81 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 15.98/ 15.98 GFLOPS | Progress: (4/20) | 4.15 s
-[Task 10/25] Current/Best: 12.47/ 15.98 GFLOPS | Progress: (8/20) | 5.99 s
-[Task 10/25] Current/Best: 13.77/ 20.67 GFLOPS | Progress: (12/20) | 9.21 s
-[Task 10/25] Current/Best: 4.43/ 20.67 GFLOPS | Progress: (16/20) | 11.45 s
-[Task 10/25] Current/Best: 8.98/ 20.67 GFLOPS | Progress: (20/20) | 14.14 s Done.
+[Task 10/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (4/20) | 4.52 s
+[Task 10/25] Current/Best: 16.33/ 20.62 GFLOPS | Progress: (8/20) | 6.67 s
+[Task 10/25] Current/Best: 13.23/ 20.62 GFLOPS | Progress: (12/20) | 8.50 s
+[Task 10/25] Current/Best: 12.28/ 20.62 GFLOPS | Progress: (16/20) | 10.53 s
+[Task 10/25] Current/Best: 5.53/ 20.62 GFLOPS | Progress: (20/20) | 12.71 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 9.94/ 15.29 GFLOPS | Progress: (4/20) | 4.44 s
-[Task 11/25] Current/Best: 19.76/ 19.76 GFLOPS | Progress: (8/20) | 6.69 s
-[Task 11/25] Current/Best: 21.08/ 21.08 GFLOPS | Progress: (12/20) | 9.34 s
-[Task 11/25] Current/Best: 13.27/ 21.08 GFLOPS | Progress: (16/20) | 13.02 s
-[Task 11/25] Current/Best: 21.84/ 21.84 GFLOPS | Progress: (20/20) | 16.91 s Done.
+[Task 11/25] Current/Best: 9.24/ 9.24 GFLOPS | Progress: (4/20) | 5.46 s
+[Task 11/25] Current/Best: 14.15/ 17.97 GFLOPS | Progress: (8/20) | 8.07 s
+[Task 11/25] Current/Best: 13.20/ 17.97 GFLOPS | Progress: (12/20) | 11.30 s
+[Task 11/25] Current/Best: 12.91/ 20.33 GFLOPS | Progress: (16/20) | 13.86 s
+[Task 11/25] Current/Best: 12.52/ 20.33 GFLOPS | Progress: (20/20) | 17.38 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 13.11/ 16.65 GFLOPS | Progress: (4/20) | 8.32 s
-[Task 12/25] Current/Best: 8.18/ 16.65 GFLOPS | Progress: (8/20) | 11.36 s
-[Task 12/25] Current/Best: 4.51/ 16.65 GFLOPS | Progress: (12/20) | 14.42 s
-[Task 12/25] Current/Best: 10.71/ 16.65 GFLOPS | Progress: (16/20) | 17.31 s
-[Task 12/25] Current/Best: 4.76/ 17.75 GFLOPS | Progress: (20/20) | 20.31 s Done.
+[Task 12/25] Current/Best: 15.36/ 15.36 GFLOPS | Progress: (4/20) | 6.64 s
+[Task 12/25] Current/Best: 15.92/ 15.92 GFLOPS | Progress: (8/20) | 10.11 s
+[Task 12/25] Current/Best: 18.43/ 18.43 GFLOPS | Progress: (12/20) | 13.32 s
+[Task 12/25] Current/Best: 15.25/ 18.43 GFLOPS | Progress: (16/20) | 16.49 s
+[Task 12/25] Current/Best: 5.08/ 18.43 GFLOPS | Progress: (20/20) | 19.34 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.42/ 20.40 GFLOPS | Progress: (4/20) | 4.20 s
-[Task 13/25] Current/Best: 15.21/ 20.40 GFLOPS | Progress: (8/20) | 6.43 s
-[Task 13/25] Current/Best: 21.06/ 21.06 GFLOPS | Progress: (12/20) | 9.63 s
-[Task 13/25] Current/Best: 9.80/ 21.06 GFLOPS | Progress: (16/20) | 12.86 s
-[Task 13/25] Current/Best: 12.39/ 21.06 GFLOPS | Progress: (20/20) | 16.16 s Done.
+[Task 13/25] Current/Best: 16.71/ 17.39 GFLOPS | Progress: (4/20) | 4.31 s
+[Task 13/25] Current/Best: 6.65/ 17.39 GFLOPS | Progress: (8/20) | 8.31 s
+[Task 13/25] Current/Best: 17.88/ 17.88 GFLOPS | Progress: (12/20) | 10.43 s
+[Task 13/25] Current/Best: 7.68/ 17.88 GFLOPS | Progress: (16/20) | 13.50 s
+[Task 13/25] Current/Best: 18.04/ 19.37 GFLOPS | Progress: (20/20) | 15.68 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 11.41/ 19.23 GFLOPS | Progress: (4/20) | 4.33 s
-[Task 14/25] Current/Best: 3.57/ 19.23 GFLOPS | Progress: (8/20) | 11.10 s
-[Task 14/25] Current/Best: 13.18/ 19.23 GFLOPS | Progress: (12/20) | 19.28 s
-[Task 14/25] Current/Best: 20.29/ 20.29 GFLOPS | Progress: (16/20) | 21.43 s
-[Task 14/25] Current/Best: 4.65/ 20.29 GFLOPS | Progress: (20/20) | 23.52 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+[Task 14/25] Current/Best: 14.24/ 14.93 GFLOPS | Progress: (4/20) | 4.06 s
+[Task 14/25] Current/Best: 10.81/ 17.45 GFLOPS | Progress: (8/20) | 8.81 s
+[Task 14/25] Current/Best: 10.26/ 17.45 GFLOPS | Progress: (12/20) | 12.59 s
+[Task 14/25] Current/Best: 3.08/ 17.45 GFLOPS | Progress: (16/20) | 17.16 s
+[Task 14/25] Current/Best: 11.43/ 17.45 GFLOPS | Progress: (20/20) | 20.19 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 15/25] Current/Best: 7.46/ 18.81 GFLOPS | Progress: (4/20) | 6.12 s Done.
Done.
-[Task 15/25] Current/Best: 12.29/ 13.28 GFLOPS | Progress: (4/20) | 4.07 s
-[Task 15/25] Current/Best: 5.92/ 16.26 GFLOPS | Progress: (8/20) | 7.76 s
-[Task 15/25] Current/Best: 6.76/ 16.26 GFLOPS | Progress: (12/20) | 10.03 s
-[Task 15/25] Current/Best: 2.64/ 18.90 GFLOPS | Progress: (16/20) | 14.60 s
-[Task 15/25] Current/Best: 5.72/ 18.90 GFLOPS | Progress: (20/20) | 17.33 s
+[Task 15/25] Current/Best: 3.15/ 18.81 GFLOPS | Progress: (8/20) | 11.56 s
+[Task 15/25] Current/Best: 7.37/ 18.81 GFLOPS | Progress: (12/20) | 21.51 s
+[Task 15/25] Current/Best: 19.48/ 20.76 GFLOPS | Progress: (16/20) | 24.95 s
+[Task 15/25] Current/Best: 15.97/ 20.76 GFLOPS | Progress: (20/20) | 30.85 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 10.56/ 18.96 GFLOPS | Progress: (4/20) | 5.02 s
-[Task 16/25] Current/Best: 13.45/ 18.96 GFLOPS | Progress: (8/20) | 6.74 s
-[Task 16/25] Current/Best: 8.52/ 18.96 GFLOPS | Progress: (12/20) | 9.31 s
-[Task 16/25] Current/Best: 16.10/ 18.96 GFLOPS | Progress: (16/20) | 11.11 s
-[Task 16/25] Current/Best: 15.28/ 18.96 GFLOPS | Progress: (20/20) | 14.98 s Done.
+[Task 16/25] Current/Best: 17.02/ 18.31 GFLOPS | Progress: (4/20) | 4.84 s
+[Task 16/25] Current/Best: 3.01/ 20.82 GFLOPS | Progress: (8/20) | 6.91 s
+[Task 16/25] Current/Best: 16.19/ 20.82 GFLOPS | Progress: (12/20) | 8.38 s
+[Task 16/25] Current/Best: 6.21/ 20.82 GFLOPS | Progress: (16/20) | 10.76 s
+[Task 16/25] Current/Best: 5.09/ 20.82 GFLOPS | Progress: (20/20) | 14.26 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 15.14/ 20.68 GFLOPS | Progress: (4/20) | 4.00 s
-[Task 17/25] Current/Best: 12.30/ 20.68 GFLOPS | Progress: (8/20) | 6.58 s
-[Task 17/25] Current/Best: 22.72/ 22.72 GFLOPS | Progress: (12/20) | 9.59 s
-[Task 17/25] Current/Best: 23.60/ 23.60 GFLOPS | Progress: (16/20) | 12.30 s
-[Task 17/25] Current/Best: 17.81/ 23.60 GFLOPS | Progress: (20/20) | 15.32 s Done.
+[Task 17/25] Current/Best: 9.82/ 20.77 GFLOPS | Progress: (4/20) | 4.46 s
+[Task 17/25] Current/Best: 14.17/ 20.77 GFLOPS | Progress: (8/20) | 7.64 s
+[Task 17/25] Current/Best: 7.66/ 20.77 GFLOPS | Progress: (12/20) | 10.35 s
+[Task 17/25] Current/Best: 18.84/ 20.77 GFLOPS | Progress: (16/20) | 12.35 s
+[Task 17/25] Current/Best: 14.93/ 20.77 GFLOPS | Progress: (20/20) | 14.78 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 19.25/ 21.38 GFLOPS | Progress: (4/20) | 4.69 s
-[Task 18/25] Current/Best: 10.27/ 21.38 GFLOPS | Progress: (8/20) | 9.08 s
-[Task 18/25] Current/Best: 17.93/ 21.38 GFLOPS | Progress: (12/20) | 13.11 s
-[Task 18/25] Current/Best: 10.33/ 21.38 GFLOPS | Progress: (16/20) | 19.04 s
-[Task 18/25] Current/Best: 16.35/ 21.38 GFLOPS | Progress: (20/20) | 25.13 s Done.
+[Task 18/25] Current/Best: 15.81/ 19.65 GFLOPS | Progress: (4/20) | 5.52 s
+[Task 18/25] Current/Best: 11.98/ 19.65 GFLOPS | Progress: (8/20) | 8.21 s
+[Task 18/25] Current/Best: 9.64/ 19.65 GFLOPS | Progress: (12/20) | 13.42 s
+[Task 18/25] Current/Best: 6.22/ 19.65 GFLOPS | Progress: (16/20) | 17.29 s
+[Task 18/25] Current/Best: 18.69/ 19.65 GFLOPS | Progress: (20/20) | 19.58 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 10.64/ 10.64 GFLOPS | Progress: (4/20) | 6.22 s
-[Task 19/25] Current/Best: 17.15/ 17.15 GFLOPS | Progress: (8/20) | 8.67 s
-[Task 19/25] Current/Best: 7.10/ 17.15 GFLOPS | Progress: (12/20) | 12.44 s
-[Task 19/25] Current/Best: 6.61/ 21.29 GFLOPS | Progress: (16/20) | 16.15 s
-[Task 19/25] Current/Best: 9.34/ 21.29 GFLOPS | Progress: (20/20) | 20.84 s Done.
+[Task 19/25] Current/Best: 10.35/ 12.57 GFLOPS | Progress: (4/20) | 5.79 s
+[Task 19/25] Current/Best: 5.23/ 18.96 GFLOPS | Progress: (8/20) | 10.01 s
+[Task 19/25] Current/Best: 10.84/ 18.96 GFLOPS | Progress: (12/20) | 13.56 s
+[Task 19/25] Current/Best: 14.41/ 23.22 GFLOPS | Progress: (16/20) | 17.61 s
+[Task 19/25] Current/Best: 3.08/ 23.22 GFLOPS | Progress: (20/20) | 20.97 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 11.18/ 11.18 GFLOPS | Progress: (4/20) | 4.27 s
-[Task 20/25] Current/Best: 16.83/ 16.83 GFLOPS | Progress: (8/20) | 7.54 s
-[Task 20/25] Current/Best: 2.06/ 16.83 GFLOPS | Progress: (12/20) | 11.75 s
-[Task 20/25] Current/Best: 15.20/ 16.83 GFLOPS | Progress: (16/20) | 13.91 s
-[Task 20/25] Current/Best: 13.35/ 16.83 GFLOPS | Progress: (20/20) | 17.13 s Done.
-
+[Task 20/25] Current/Best: 13.69/ 18.53 GFLOPS | Progress: (4/20) | 4.07 s
+[Task 20/25] Current/Best: 7.35/ 18.53 GFLOPS | Progress: (8/20) | 7.77 s
+[Task 20/25] Current/Best: 12.26/ 18.53 GFLOPS | Progress: (12/20) | 9.93 s
+[Task 20/25] Current/Best: 12.21/ 18.53 GFLOPS | Progress: (16/20) | 13.07 s
+[Task 20/25] Current/Best: 10.53/ 18.53 GFLOPS | Progress: (20/20) | 16.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 19.85/ 19.85 GFLOPS | Progress: (4/20) | 3.41 s
-[Task 21/25] Current/Best: 19.51/ 19.85 GFLOPS | Progress: (8/20) | 5.52 s
-[Task 21/25] Current/Best: 13.60/ 19.85 GFLOPS | Progress: (12/20) | 7.75 s
-[Task 21/25] Current/Best: 11.89/ 19.85 GFLOPS | Progress: (16/20) | 10.30 s
-[Task 21/25] Current/Best: 16.12/ 19.85 GFLOPS | Progress: (20/20) | 11.86 s
+[Task 21/25] Current/Best: 10.51/ 12.00 GFLOPS | Progress: (4/20) | 3.42 s
+[Task 21/25] Current/Best: 16.73/ 17.81 GFLOPS | Progress: (8/20) | 5.63 s Done.
+
+[Task 21/25] Current/Best: 21.95/ 21.95 GFLOPS | Progress: (12/20) | 8.65 s
+[Task 21/25] Current/Best: 19.18/ 21.95 GFLOPS | Progress: (16/20) | 10.64 s
+[Task 21/25] Current/Best: 17.10/ 21.95 GFLOPS | Progress: (20/20) | 13.23 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 6.31/ 16.08 GFLOPS | Progress: (4/20) | 4.34 s
-[Task 22/25] Current/Best: 7.96/ 16.08 GFLOPS | Progress: (8/20) | 6.05 s
-[Task 22/25] Current/Best: 11.26/ 16.14 GFLOPS | Progress: (12/20) | 8.24 s
-[Task 22/25] Current/Best: 9.32/ 21.96 GFLOPS | Progress: (16/20) | 10.08 s
-[Task 22/25] Current/Best: 5.18/ 21.96 GFLOPS | Progress: (20/20) | 11.74 s Done.
+[Task 22/25] Current/Best: 17.55/ 18.17 GFLOPS | Progress: (4/20) | 3.74 s
+[Task 22/25] Current/Best: 9.62/ 18.17 GFLOPS | Progress: (8/20) | 7.59 s
+[Task 22/25] Current/Best: 12.15/ 18.17 GFLOPS | Progress: (12/20) | 10.82 s
+[Task 22/25] Current/Best: 15.39/ 18.17 GFLOPS | Progress: (16/20) | 12.83 s
+[Task 22/25] Current/Best: 13.97/ 18.17 GFLOPS | Progress: (20/20) | 18.37 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 3.08/ 9.55 GFLOPS | Progress: (4/20) | 6.13 s
-[Task 23/25] Current/Best: 16.46/ 20.03 GFLOPS | Progress: (8/20) | 9.56 s
-[Task 23/25] Current/Best: 18.69/ 22.24 GFLOPS | Progress: (12/20) | 12.88 s
-[Task 23/25] Current/Best: 23.13/ 23.13 GFLOPS | Progress: (16/20) | 16.56 s
-[Task 23/25] Current/Best: 8.93/ 23.13 GFLOPS | Progress: (20/20) | 19.70 s Done.
+[Task 23/25] Current/Best: 9.45/ 17.77 GFLOPS | Progress: (4/20) | 5.70 s
+[Task 23/25] Current/Best: 8.21/ 19.36 GFLOPS | Progress: (8/20) | 8.98 s
+[Task 23/25] Current/Best: 2.38/ 19.36 GFLOPS | Progress: (12/20) | 12.63 s
+[Task 23/25] Current/Best: 18.59/ 22.40 GFLOPS | Progress: (16/20) | 14.97 s
+[Task 23/25] Current/Best: 11.10/ 22.40 GFLOPS | Progress: (20/20) | 19.25 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 10.16/ 10.16 GFLOPS | Progress: (4/20) | 12.19 s
-[Task 24/25] Current/Best: 9.51/ 10.16 GFLOPS | Progress: (8/20) | 24.04 s Done.
-
-[Task 24/25] Current/Best: 3.50/ 10.16 GFLOPS | Progress: (12/20) | 36.25 s
-[Task 24/25] Current/Best: 4.56/ 10.16 GFLOPS | Progress: (16/20) | 47.19 s
-[Task 24/25] Current/Best: 3.72/ 10.16 GFLOPS | Progress: (20/20) | 58.18 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 3.88/ 5.21 GFLOPS | Progress: (4/20) | 13.41 s
-[Task 25/25] Current/Best: 7.94/ 8.47 GFLOPS | Progress: (8/20) | 16.18 s
-[Task 25/25] Current/Best: 9.10/ 9.10 GFLOPS | Progress: (12/20) | 21.67 s
-[Task 25/25] Current/Best: 5.74/ 9.10 GFLOPS | Progress: (16/20) | 27.23 s
-[Task 25/25] Current/Best: 7.48/ 9.10 GFLOPS | Progress: (20/20) | 31.22 s Done.
+[Task 24/25] Current/Best: 3.37/ 9.71 GFLOPS | Progress: (4/20) | 12.84 s
+[Task 24/25] Current/Best: 5.35/ 9.71 GFLOPS | Progress: (8/20) | 24.65 s
+[Task 24/25] Current/Best: 2.18/ 9.71 GFLOPS | Progress: (12/20) | 36.23 s
+[Task 24/25] Current/Best: 1.66/ 9.71 GFLOPS | Progress: (16/20) | 48.15 s
+[Task 24/25] Current/Best: 5.77/ 9.71 GFLOPS | Progress: (20/20) | 60.07 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
+[Task 25/25] Current/Best: 2.96/ 8.22 GFLOPS | Progress: (4/20) | 13.87 s
+[Task 25/25] Current/Best: 1.54/ 9.09 GFLOPS | Progress: (8/20) | 16.07 s
+[Task 25/25] Current/Best: 7.50/ 9.09 GFLOPS | Progress: (12/20) | 27.01 s
+[Task 25/25] Current/Best: 7.97/ 9.09 GFLOPS | Progress: (16/20) | 29.54 s
+[Task 25/25] Current/Best: 2.96/ 9.09 GFLOPS | Progress: (20/20) | 39.91 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -943,7 +945,7 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+<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='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -981,8 +983,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 411.8653575500002, 'median': 411.6579371999933, 'std': 2.2107734226906803}
-unoptimized: {'mean': 513.194206589999, 'median': 512.949942749998, 'std': 2.1665419819072995}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 434.05912445999775, 'median': 433.28455185001076, 'std': 2.978056187539585}
+unoptimized: {'mean': 523.192951289999, 'median': 523.8391569499925, 'std': 2.481909805515635}
</pre></div>
</div>
</div>
@@ -996,7 +998,7 @@ 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> ( 11 minutes 47.427 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 4.273 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 01623c553a..343282da6d 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.26e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.244e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index a2832b2bbb..549e12e4d4 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -494,7 +494,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x213d8c10)), stage(b, placeholder(b, 0x28371bf0)), 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, 0x24556490)), stage(b, placeholder(b, 0x12a65690)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index e967ab1cac..69f69dafc7 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:04.807</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:24.298</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>11:47.427</p></td>
+<td><p>12:04.273</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:13.124</p></td>
+<td><p>01:15.424</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.694</p></td>
+<td><p>01:02.845</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:34.372</p></td>
+<td><p>00:34.940</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:25.721</p></td>
+<td><p>00:24.413</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.450</p></td>
+<td><p>00:01.349</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.835</p></td>
+<td><p>00:00.855</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.173</p></td>
+<td><p>00:00.189</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
@@ -385,10 +385,10 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.002</p></td>
+<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
@@ -396,7 +396,7 @@
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 65516f3ff2..efe6368f96 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -551,8 +551,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000009
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -639,7 +639,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000027
@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, [n: int32], [stride: int32], type="auto"),
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.5752199995804405e-06 1.0
- naive 8.6728e-06 1.14489084151752
-parallel 6.9837000000000006e-06 0.9219138190556576
- vector 2.45603e-05 3.242189665958255
+ numpy 6.524820000777254e-06 1.0
+ naive 6.7542e-06 1.0351549926580996
+parallel 6.9875000000000004e-06 1.0709107682920955
+ vector 2.65005e-05 4.0614913510017425
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -990,7 +990,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018597
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019067
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1031,7 +1031,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.467281
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.478545
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1095,7 +1095,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.293226
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.333455
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1153,7 +1153,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.333874
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.355765
@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, [1024, 1024], []),
@@ -1207,7 +1207,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.117445
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.137987
@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, [1024, 1024], []),
@@ -1282,7 +1282,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109663
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110269
@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, [1024, 1024], []),
@@ -1355,7 +1355,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111546
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.112124
@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, [1024, 1024], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.148143
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.147456
@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, [1024, 1024], []),
@@ -1482,13 +1482,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4672807165000004 1.0
- blocking 0.2932257556 0.0845693728242439
- vectorization 0.3338737371 0.09629267555729504
-loop permutation 0.11744508470000001 0.0338723900090078
- array packing 0.1096628929 0.031627924551403994
- block caching 0.1115455265 0.032170895759659784
- parallelization 0.1481426293 0.0427258827342773
+ none 3.4785447568000003 1.0
+ blocking 0.333455125 0.09586052453347005
+ vectorization 0.3557646123 0.10227397868161303
+loop permutation 0.1379866034 0.03966791087861043
+ array packing 0.11026868370000001 0.03169965931426994
+ block caching 0.1121242066 0.03223307861162777
+ parallelization 0.14745647580000001 0.04239027700067568
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1520,7 +1520,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.694 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.845 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>