You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/10/27 21:29:08 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@5acf3f90c63b6760cd23796b442f8ac20e645af0)
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 24dfb9cff9 deploying docs (apache/tvm@5acf3f90c63b6760cd23796b442f8ac20e645af0)
24dfb9cff9 is described below
commit 24dfb9cff94beead388f48e6ee0629ab9bbbb66c
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Oct 27 21:29:00 2022 +0000
deploying docs (apache/tvm@5acf3f90c63b6760cd23796b442f8ac20e645af0)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 332113 -> 335230 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23380 -> 23974 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 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 | 823 ++++++++++++++++-----
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 84 ++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 722 +++++++-----------
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 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 | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../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_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 12 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 42 +-
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 | 18 +-
.../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 | 823 ++++++++++++++++-----
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 84 ++-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 722 +++++++-----------
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/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 | 267 ++++---
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
125 files changed, 2711 insertions(+), 2129 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 0fd9c0ef04..4730ebaecb 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 2b4fe4d842..4f63c99e35 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 406f1cf1ac..483b69857b 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 11.923 seconds)
+ **Total running time of the script:** ( 1 minutes 11.135 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index ffeebdf485..d84df4a264 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 967ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 960ms/step
Keras top-1 id: 285, class name: Egyptian cat
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 814dfc168d..13eac7c7fc 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.zip2ac2aad8-5672-4203-94d1-13b04497c543 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4d6e2683-624a-4385-a42e-aae535fa608c 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 ade300187a..f820cd937c 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, 37.3MB/s]
38%|###7 | 15.7M/41.5M [00:00<00:00, 54.2MB/s]
52%|#####2 | 21.7M/41.5M [00:00<00:00, 53.7MB/s]
66%|######5 | 27.3M/41.5M [00:00<00:00, 47.3MB/s]
77%|#######7 | 32.1M/41.5M [00:00<00:00, 47.4MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 44.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 46.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
25%|##5 | 10.4M/41.5M [00:00<00:00, 109MB/s]
50%|##### | 20.8M/41.5M [00:00<00:00, 87.8MB/s]
71%|####### | 29.4M/41.5M [00:00<00:00, 75.2MB/s]
89%|########8 | 36.8M/41.5M [00:00<00:00, 70.5MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 64.9MB/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 c88964a831..6efe648c1c 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]
31%|###1 | 14.0M/44.7M [00:00<00:00, 147MB/s]
63%|######3 | 28.2M/44.7M [00:00<00:00, 148MB/s]
95%|#########4| 42.3M/44.7M [00:00<00:00, 99.8MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 112MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 8.01M/44.7M [00:00<00:00, 83.8MB/s]
45%|####4 | 20.0M/44.7M [00:00<00:00, 109MB/s]
68%|######8 | 30.4M/44.7M [00:00<00:00, 109MB/s]
91%|#########1| 40.8M/44.7M [00:00<00:00, 103MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index e37897c71b..68c056568a 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 11.647 seconds)
+ **Total running time of the script:** ( 1 minutes 11.534 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 df9985ac7b..064c8875f0 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
=================
-**05:46.095** total execution time for **how_to_compile_models** files:
+**05:45.975** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.923 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.534 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.647 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.135 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.026 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.380 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.977 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.801 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.268 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.876 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.618 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.603 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.981 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.146 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.980 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.723 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.318 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.386 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.357 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.391 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 678b2a371b..80d6b6c0db 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
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.5495 16.7429 17.0968 15.7640 0.4404
+ 15.8826 15.8755 16.0334 15.7582 0.0801
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 866f023514..fffefadf37 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%|5 | 9.21M/170M [00:00<00:01, 96.6MB/s]
11%|# | 18.4M/170M [00:00<00:02, 73.6MB/s]
15%|#5 | 25.8M/170M [00:00<00:02, 71.2MB/s]
19%|#9 | 32.7M/170M [00:00<00:02, 66.2MB/s]
25%|##4 | 42.1M/170M [00:00<00:01, 72.2MB/s]
30%|##9 | 50.4M/170M [00:00<00:01, 76.3MB/s]
36%|###6 | 61.8M/170M [00:00<00:01, 88.9MB/s]
42%|####2 | 72.0M/170M [00:00<00:01, 93.3MB/s]
48%|####7 | 81.4M/170M [00:01<00:00, 94.7MB/s]
53%|#####3 | 90.7M/170M [00:01<00:00, 95.5MB/s]
59%|#####8 | 99.9M/170M [00:01<00:00, 91.9MB/s]
66%|######5 | 111M/170M [00:01<00:00, 100MB/s]
71%|#######1 | 121M/170M [00:01<00:00, 86.1MB/s]
76%|#######6 | 130M/170M [00:01<00:00, 83.3MB/s]
81%|########1 | 138M/170M [00:01<00:00, 85.2MB/s]
86%|########6 | 147M/170M [00:01<00:00, 85.1MB/s]
92%|#########2| 157M/170M [00:01<00:00, 91.8MB/s]
98%|#########7| 166M/170M [00:02<00:00, 92.0MB/s]
100%|##########| 170M/170M [00:02<00:00, 87.5MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 70.6MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 73.8MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 75.5MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 65.1MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 65.7MB/s]
28%|##8 | 48.0M/170M [00:00<00:02, 56.5MB/s]
33%|###3 | 56.3M/170M [00:00<00:01, 64.0MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 66.7MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 71.1MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 70.4MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 71.4MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 72.2MB/s]
61%|######1 | 104M/170M [00:01<00:00, 71.1MB/s]
66%|######5 | 112M/170M [00:01<00:00, 64.4MB/s]
71%|####### | 120M/170M [00:01<00:00, 68.1MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 71.2MB/s]
81%|######## | 137M/170M [00:02<00:00, 78.0MB/s]
85%|########5 | 145M/170M [00:02<00:00, 76.6MB/s]
92%|#########1| 156M/170M [00:02<00:00, 87.3MB/s]
97%|#########6| 164M/170M [00:02<00:00, 81.2MB/s]
100%|##########| 170M/170M [00:02<00:00, 73.2MB/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 16.545 seconds)
+ **Total running time of the script:** ( 3 minutes 16.979 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 08f62aa8b1..3efc54d613 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, 48.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 73.0MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 71.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 101MB/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)
- 90.5043 90.2555 105.2862 89.9734 1.5511
+ 90.2623 90.2032 90.8305 89.9470 0.1946
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.984 seconds)
+ **Total running time of the script:** ( 1 minutes 4.915 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 339a4f36e2..3b1988f3b2 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)
- 120.3099 120.2600 125.4839 119.3358 0.7139
+ 120.9118 120.9551 121.7318 119.8852 0.3764
@@ -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 31.372 seconds)
+ **Total running time of the script:** ( 2 minutes 29.342 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 f2730ecace..59be0c7d80 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 27.332 seconds)
+ **Total running time of the script:** ( 1 minutes 26.368 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 fadb9531ea..a8c432d805 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]
1%|1 | 1405/132723 [00:00<00:09, 13936.64KB/s]
3%|2 | 3869/132723 [00:00<00:06, 19965.20KB/s]
6%|6 | 7965/132723 [00:00<00:04, 29404.06KB/s]
11%|#1 | 14695/132723 [00:00<00:02, 44265.33KB/s]
18%|#7 | 23357/132723 [00:00<00:01, 59473.39KB/s]
24%|##4 | 32061/132723 [00:00<00:01, 68816.74KB/s]
31%|### | 40767/132723 [00:00<00:01, 74767.77KB/s]
37%|###7 | 49488/132723 [00:00<00:01, 78720.54KB/s]
44%|####3 | 58220/132723 [00:00<00:00, 81404.13KB/s]
51%|##### | 67053/132723 [00:01<00:00, 83533.09KB/s]
57%|#####7 | 75861/132723 [00:01<00:00, 84920.44KB/s]
64%|######3 | 84416/132723 [00:01<00:00, 85109.63KB/s]
70%|####### | 93221/132723 [00:01<00:00, 85998.33KB/s]
77%|#######6 | 102097/132723 [00:01<00:00, 86830.83KB/s]
84%|########3 | 110909/132723 [00:01<00:00, 87212.87KB/s]
90%|######### |
119714/132723 [00:01<00:00, 87461.44KB/s]
97%|#########6| 128560/132723 [00:01<00:00, 87758.54KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75713.63KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
1%|1 | 1784/132723 [00:00<00:07, 17564.22KB/s]
4%|3 | 5256/132723 [00:00<00:04, 27552.80KB/s]
9%|8 | 11765/132723 [00:00<00:02, 44619.12KB/s]
15%|#5 | 20185/132723 [00:00<00:01, 60201.27KB/s]
22%|##1 | 28566/132723 [00:00<00:01, 68697.86KB/s]
28%|##7 | 37096/132723 [00:00<00:01, 74330.63KB/s]
34%|###4 | 45630/132723 [00:00<00:01, 77925.59KB/s]
41%|#### | 54182/132723 [00:00<00:00, 80338.64KB/s]
47%|####7 | 62772/132723 [00:00<00:00, 82074.61KB/s]
54%|#####3 | 71320/132723 [00:01<00:00, 83123.61KB/s]
60%|###### | 79936/132723 [00:01<00:00, 84050.20KB/s]
67%|######6 | 88493/132723 [00:01<00:00, 84507.09KB/s]
73%|#######3 | 96945/132723 [00:01<00:00, 84158.72KB/s]
79%|#######9 | 105469/132723 [00:01<00:00, 84481.26KB/s]
86%|########5 | 113918/132723 [00:01<00:00, 84392.95KB/s]
92%|#########2
| 122469/132723 [00:01<00:00, 84724.32KB/s]
99%|#########8| 131015/132723 [00:01<00:00, 84943.87KB/s]
100%|##########| 132723/132723 [00:01<00:00, 76895.56KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 58.330 seconds)
+ **Total running time of the script:** ( 2 minutes 57.204 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 e73ecf2c76..53b126bda8 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:46.106** total execution time for **how_to_deploy_models** files:
+**12:41.628** 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``) | 03:16.545 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:16.979 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:58.330 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:57.204 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:31.372 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:29.342 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:27.332 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:26.368 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.984 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:04.915 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.724 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.620 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.490 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.659 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.322 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.534 | 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 128ab54832..21d0a54270 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.zipbca5da70-3120-40a7-b5d7-1ba9ea749349 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7f87b484-f896-4e08-8ee7-ce074ed2f7fa 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 245151b127..cd790798a3 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
=================
-**00:46.920** total execution time for **how_to_extend_tvm** files:
+**00:48.028** 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``) | 00:43.378 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.613 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.457 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.391 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.076 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.014 | 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 2c28fe05f4..292ae7b7f3 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: 6878us [6878us] (46.00%; 46.00%)
- FoldScaleAxis: 8074us [6us] (54.00%; 54.00%)
- FoldConstant: 8068us [1752us] (53.96%; 99.92%)
- InferType: 6316us [6316us] (42.24%; 78.28%)
+ InferType: 6694us [6694us] (46.71%; 46.71%)
+ FoldScaleAxis: 7638us [5us] (53.29%; 53.29%)
+ FoldConstant: 7633us [1528us] (53.26%; 99.93%)
+ InferType: 6105us [6105us] (42.60%; 79.98%)
@@ -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: 6312us [6312us] (44.47%; 44.47%)
- FoldScaleAxis: 7880us [5us] (55.53%; 55.53%)
- FoldConstant: 7875us [1704us] (55.49%; 99.94%)
- InferType: 6171us [6171us] (43.48%; 78.36%)
+ InferType: 6110us [6110us] (44.75%; 44.75%)
+ FoldScaleAxis: 7545us [5us] (55.25%; 55.25%)
+ FoldConstant: 7540us [1528us] (55.22%; 99.94%)
+ InferType: 6013us [6013us] (44.03%; 79.74%)
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 f534f13104..9cadd0a830 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.258209 ms
+ Convolution: 39.235359 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 b98f8bb6d8..f4395c6e50 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
@@ -659,7 +659,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 11.481488 ms
+ conv2d with tensor core: 12.416918 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 f3daff8207..2e9e380c38 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: 0.018914
- Baseline: 3.350183
+ Numpy running time: 0.019147
+ Baseline: 3.365475
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.317286
+ Opt1: 0.308592
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.346113
+ Opt2: 0.349700
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.119121
+ Opt3: 0.127762
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110715
+ Opt4: 0.110178
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111440
+ Opt5: 0.111495
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147520
+ Opt6: 0.147570
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 cd1188ca38..41bcdb840a 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
=================
-**00:35.043** total execution time for **how_to_optimize_operators** files:
+**00:35.285** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.688 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.387 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.440 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.111 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.157 | 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 404cb52719..d844121288 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
=================
-**08:23.741** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:27.418** 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``) | 04:57.188 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:02.010 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.267 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.568 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:03.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.662 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:26.479 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.365 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.063 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.728 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.174 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.086 | 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 23ea635e25..af5217eea3 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,105 +240,346 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), 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" = 49 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 128) {
- let cse_var_1: int32 = (rc.outer.outer*36)
+ 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)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[(threadIdx.x_1*9)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*9) + 1)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 2)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 6)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 3)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 5)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 4)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 4)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 5)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 3)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 6)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 2)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 7)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 1)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 8)] = 0f32
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*48)] = @tir.if_then_else((((3 <= floormod((threadIdx.x_1*16), 27)) && (floormod((threadIdx.x_1*48), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 27)*49)) + (floordiv(floormod((threadIdx.x_1*16), 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 1)] = @tir.if_then_else(((3 <= floormod((threadIdx.x_1*16), 27)) && (floormod(((threadIdx.x_1*48) + 1), 81) < 72)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 27)*49)) + (floordiv(floormod((threadIdx.x_1*16), 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2)] = @tir.if_then_else((((3 <= floormod((threadIdx.x_1*16), 27)) && (floormod(((threadIdx.x_1*48) + 2), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 27)*49)) + (floordiv(floormod((threadIdx.x_1*16), 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 9)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 9), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 10)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 10), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 11)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 11), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 12)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 4), 27)) && (floormod(((threadIdx.x_1*48) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 13)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 4), 27)) && (floormod(((threadIdx.x_1*48) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 14)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 4), 27)) && (floormod(((threadIdx.x_1*48) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 15)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 16)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 17)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 18)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 18), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 19)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 19), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 20)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 20), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 21)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 22)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 23)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 24)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 25)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 26)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 26), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 27)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 27), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 28)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 28), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 29)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 29), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 30)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 30), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 31)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 31), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 32)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 32), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 33)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 33), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 34)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 34), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 35)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 35), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 36)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 37)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 37), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 38)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 38), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 39)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 39), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 40)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 40), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 41)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 41), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 42)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 42), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 43)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 44)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 44), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 45)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 45), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 46)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 46), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 47)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 47), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 98), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 26), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 294), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 6), 36), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 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" = 98;
- if @tir.likely((threadIdx.x_2 < 86), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 490), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 22), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2352)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2353)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2354)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2355)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2356)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2357)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2358)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 9), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 786), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2359)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 10), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 786), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2360)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 11), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 786), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2361)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 787), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype= [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2362)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 787), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype= [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2363)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 787), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype= [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2364)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 788), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2365)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 788), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2366)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 788), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2367)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 18), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 789), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2368)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 19), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 789), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2369)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 20), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 789), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2370)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 790), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2371)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 790), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2372)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 790), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2373)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 791), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2374)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 791), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2375)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 26), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 791), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2376)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 27), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 792), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2377)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 28), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 792), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2378)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 29), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 792), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2379)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 30), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 793), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2380)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 31), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 793), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2381)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 32), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 793), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2382)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 33), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 794), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2383)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 34), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 794), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2384)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 35), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 794), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2385)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 795), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2386)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 37), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 795), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2387)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 38), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 795), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2388)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 39), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 796), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2389)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 40), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 796), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2390)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 41), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 796), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2391)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 42), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 797), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2392)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 797), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2393)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 44), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 797), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2394)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 45), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 798), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2395)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 46), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 798), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2396)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 47), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 798), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2397)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 16), 27)) && (floormod(((threadIdx.x_1*48) + 48), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 799), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2398)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 16), 27)) && (floormod(((threadIdx.x_1*48) + 49), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 799), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2399)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 16), 27)) && (floormod(((threadIdx.x_1*48) + 50), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 799), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*18432) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 49), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 98), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((blockIdx.x*18432) + cse_var_1) + threadIdx.x_2) + 147)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 196), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 245), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 245), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 294), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 343), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 55), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*18432) + (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" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 441), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 51)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 490), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 202), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 539), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 251), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 588), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 637), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 61), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 686), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 735), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 53)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*18432) + (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" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 833)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 833), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 257), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 882), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 6)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 931)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 931), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 67), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 980), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 1029)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 1029), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 55)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 1078), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 214), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_2 < 25), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1127)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 1127), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 263), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
}
- for (rc.outer.inner: int32, 0, 2) {
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 288)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 324)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 289)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 325)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 290)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 326)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 297)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 333)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 298)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 334)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 299)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 335)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 360)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 396)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 361)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 397)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 362)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 398)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 369)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 405)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 370)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 406)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 371)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 407)]))
+ for (rc.outer.inner: int32, 0, 16) {
+ let cse_var_3: int32 = (rc.outer.inner*18)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_3]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 288)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 576)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 864)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 289)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 577)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 865)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 290)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 578)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 866)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 291)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 579)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 867)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 292)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 580)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 868)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 293)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 581)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 869)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 294)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 582)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 870)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 295)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 583)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 871)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 296)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 584)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 872)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 297)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 873)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 298)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 586)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 874)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 299)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 587)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 875)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 300)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 588)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 876)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 301)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 589)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 877)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 302)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 590)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 878)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 303)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 591)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 879)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 304)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 592)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 880)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 305)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 593)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 881)]))
}
}
}
}
for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 8)]), 0f32)
+ compute[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*4) + i1.inner)]), 0f32)
}
}
}
@@ -393,7 +634,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.275 ms
+ Execution time of this operator: 0.335 ms
@@ -441,10 +682,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
@@ -454,9 +695,9 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ 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_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
@@ -464,8 +705,8 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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)
@@ -490,14 +731,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=9)
+ 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=48)
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=98)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -515,96 +756,312 @@ 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__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[324];
- __shared__ float kernel_shared[576];
+ extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[4];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[(((int)threadIdx.x) * 9)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 9) + 1)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 2)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 3)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 5)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 4)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 4)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 5)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 3)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 6)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 2)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 7)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 1)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 8)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 26) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 6) % 36) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 86) {
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 22) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ pad_temp_shared[(((int)threadIdx.x) * 48)] = ((((3 <= ((((int)threadIdx.x) * 16) % 27)) && (((((int)threadIdx.x) * 48) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 16) / 27) * 49)) + ((((((int)threadIdx.x) * 16) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 1)] = (((3 <= ((((int)threadIdx.x) * 16) % 27)) && ((((((int)threadIdx.x) * 48) + 1) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 16) / 27) * 49)) + ((((((int)threadIdx.x) * 16) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2)] = ((((3 <= ((((int)threadIdx.x) * 16) % 27)) && ((((((int)threadIdx.x) * 48) + 2) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 16) / 27) * 49)) + ((((((int)threadIdx.x) * 16) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 3)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 4)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 5)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 6)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 7)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 8)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 9)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 9) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 10)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 10) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 11)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 11) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 12)] = (((((3 <= (((((int)threadIdx.x) * 16) + 4) % 27)) && ((((((int)threadIdx.x) * 48) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 13)] = (((((3 <= (((((int)threadIdx.x) * 16) + 4) % 27)) && ((((((int)threadIdx.x) * 48) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 14)] = (((((3 <= (((((int)threadIdx.x) * 16) + 4) % 27)) && ((((((int)threadIdx.x) * 48) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 15)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 16)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 17)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 18)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 18) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 19)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 19) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 20)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 20) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 21)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 22)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 23)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 24)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 25)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 26)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 26) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 27)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 27) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 28)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 28) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 29)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 29) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 30)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 30) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 31)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 31) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 32)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 32) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 33)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 33) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 34)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 34) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 35)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 35) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 36)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 37)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 37) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 38)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 38) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 39)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 39) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 40)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 40) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 41)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 41) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 42)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 42) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 14) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 43)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 14) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 44)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 44) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 14) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 45)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 45) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 15) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 46)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 46) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 15) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 47)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 47) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 15) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2352)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2353)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2354)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2355)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2356)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2357)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2358)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 9) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 786) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2359)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 10) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 786) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2360)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 11) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 786) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2361)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 787) / 27) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2362)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 787) / 27) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2363)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 787) / 27) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2364)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 788) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2365)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 788) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2366)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 788) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2367)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 18) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 789) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2368)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 19) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 789) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2369)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 20) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 789) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2370)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 790) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2371)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 790) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2372)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 790) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2373)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 791) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2374)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 791) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2375)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 26) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 791) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2376)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 27) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 792) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2377)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 28) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 792) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2378)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 29) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 792) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2379)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 30) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 793) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2380)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 31) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 793) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2381)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 32) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 793) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2382)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 33) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 794) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2383)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 34) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 794) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2384)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 35) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 794) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2385)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 795) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2386)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 37) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 795) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2387)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 38) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 795) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2388)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 39) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 796) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2389)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 40) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 796) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2390)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 41) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 796) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2391)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 42) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 797) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2392)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 797) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2393)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 44) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 797) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2394)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 45) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 798) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2395)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 46) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 798) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2396)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 47) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 798) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2397)] = (((((3 <= (((((int)threadIdx.x) * 16) + 16) % 27)) && ((((((int)threadIdx.x) * 48) + 48) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 799) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2398)] = (((((3 <= (((((int)threadIdx.x) * 16) + 16) % 27)) && ((((((int)threadIdx.x) * 48) + 49) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 799) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2399)] = (((((3 <= (((((int)threadIdx.x) * 16) + 16) % 27)) && ((((((int)threadIdx.x) * 48) + 50) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 799) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 49) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 98) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 147)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 196) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 245) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 245) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 343) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 55) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((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) + 441)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 441) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 153)];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 490) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 202) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 539)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 539) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 251) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 637)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 637) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 61) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 686) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 110) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 735)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 735) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 159)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((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) + 833)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 833) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 257) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 882) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 18)];
+ kernel_shared[(((int)threadIdx.x) + 931)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 931) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 67) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 116) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 1029) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 165)];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 1078) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 214) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 25) {
+ kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 1127) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 263) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 288)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 324)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 289)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 325)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 290)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 326)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 297)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 333)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 298)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 334)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 299)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 335)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 360)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 396)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 361)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 397)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 362)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 398)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 369)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 405)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 370)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 406)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 371)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 407)]));
- }
+ for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_outer_inner * 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 18) + 288)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 18) + 576)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 18) + 864)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 18) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 18) + 289)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 18) + 577)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 18) + 865)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 18) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 18) + 290)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 18) + 578)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 18) + 866)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 18) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 18) + 291)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 18) + 579)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 18) + 867)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 18) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 18) + 292)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 18) + 580)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 18) + 868)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 18) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 18) + 293)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 18) + 581)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 18) + 869)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 18) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 18) + 294)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 18) + 582)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 18) + 870)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 18) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 18) + 295)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 18) + 583)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 18) + 871)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 18) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 18) + 296)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 18) + 584)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 18) + 872)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 18) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 18) + 297)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 18) + 585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 18) + 873)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 18) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 18) + 298)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 18) + 586)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 18) + 874)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 18) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 18) + 299)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 18) + 587)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 18) + 875)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 18) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 18) + 300)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 18) + 588)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 18) + 876)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 18) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 18) + 301)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 18) + 589)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 18) + 877)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 18) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 18) + 302)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 18) + 590)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 18) + 878)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 18) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 18) + 303)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 18) + 591)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 18) + 879)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 18) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 18) + 304)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 18) + 592)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 18) + 880)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 18) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 18) + 305)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 18) + 593)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 18) + 881)]));
}
}
for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
}
}
@@ -666,7 +1123,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 57.188 seconds)
+ **Total running time of the script:** ( 5 minutes 2.010 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 94f11283a4..2081f86e53 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)
- 8.2833 8.2820 8.2873 8.2807 0.0029
+ 8.1728 8.1735 8.1798 8.1650 0.0061
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.571 seconds)
+ **Total running time of the script:** ( 1 minutes 2.662 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 3b5da5d73a..dc0637454b 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)
- 752.9399 751.8006 755.6409 751.3783 1.9177
+ 757.9659 758.9378 759.4680 755.4919 1.7627
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.267 seconds)
+ **Total running time of the script:** ( 1 minutes 32.568 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 23539667a4..cbd3717715 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
@@ -386,32 +386,78 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 4) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 4) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 32) {
+ 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*8192) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*1024) + (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_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
- }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -467,7 +513,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.464 ms
+ Execution time of this operator: 1.775 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 c3c19555ca..8441b5ad48 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.075** total execution time for **how_to_tune_with_autotvm** files:
+**00:29.296** 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``) | 00:43.039 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:29.260 | 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 |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 8b50fcd9be..a8b37f62b0 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
@@ -387,8 +387,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10223830
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9834524
+ No: 2 GFLOPS: 1.91/1.91 result: MeasureResult(costs=(0.12134703050000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.425949811935425, timestamp=1666901230.1270561) [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3099700
+ No: 3 GFLOPS: 0.00/1.91 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -510,8 +511,10 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4448839
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4418916
+ No: 4 GFLOPS: 8.32/8.32 result: MeasureResult(costs=(0.02781081575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8165857791900635, timestamp=1666901232.8728542) [('tile_f', [-1, 1, 4, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8910647
+ No: 5 GFLOPS: 223.21/223.21 result: MeasureResult(costs=(0.001037167175257732,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4189164638519287, timestamp=1666901234.458369) [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7210757
+ No: 6 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -633,8 +636,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8935055
- No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7796357
+ No: 7 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -756,8 +759,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3220060
- No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6707656
+ No: 8 GFLOPS: 1.00/223.21 result: MeasureResult(costs=(0.23187986749999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.052842855453491, timestamp=1666901238.7628863) [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5243028
+ No: 9 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -879,9 +883,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,500929
- No: 6 GFLOPS: 31.87/31.87 result: MeasureResult(costs=(0.0072641439375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.912257194519043, timestamp=1666868320.6701288) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7120334
- No: 7 GFLOPS: 0.00/31.87 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5094387
+ No: 10 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1003,8 +1006,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10120885
- No: 8 GFLOPS: 0.00/31.87 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7763337
+ No: 11 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,8 +1129,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4962390
- No: 9 GFLOPS: 0.00/31.87 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7140125
+ No: 12 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,162 +1252,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10422980
- No: 10 GFLOPS: 70.99/70.99 result: MeasureResult(costs=(0.003260988285714286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6510119438171387, timestamp=1666868326.9700677) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1799056
- No: 11 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 143, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 71, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007fb94ffccfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
- Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6428638
- No: 12 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2309677
+ No: 13 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1526,161 +1375,131 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5680057
- No: 13 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5714279
+ No: 14 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ 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 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ 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):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 143, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 71, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007f3392bdbfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:1750
+ 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:1694
+ 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:1618
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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
+ 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 871, 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):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1778683
- No: 14 GFLOPS: 0.00/70.99 result: 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:1750
+ 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:1694
+ 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:1618
+ 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 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,926540
+ No: 15 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1802,161 +1621,131 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3264168
- No: 15 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6254031
+ No: 16 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ 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 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ 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):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 143, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 71, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007fb94ffccfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:1750
+ 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:1694
+ 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:1618
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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
+ 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 871, 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):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4052180
- No: 16 GFLOPS: 0.00/70.99 result: 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:1750
+ 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:1694
+ 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:1618
+ 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 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8224403
+ No: 17 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2078,8 +1867,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4853360
- No: 17 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,827316
+ No: 18 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2201,9 +1990,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9713552
- No: 18 GFLOPS: 7.84/70.99 result: MeasureResult(costs=(0.029541336,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1404051780700684, timestamp=1666868342.323972) [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5395338
- No: 19 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7775301
+ No: 19 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2325,8 +2113,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1533209
- No: 20 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1152410
+ No: 20 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2448,7 +2236,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,685169
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4209676
@@ -2503,9 +2291,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1799056
+ [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7210757
Finish loading 20 records
- Time cost of this operator: 0.002250
+ Time cost of this operator: 0.001410
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 d68706a92d..f27d31a006 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
@@ -327,10 +327,10 @@ 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 312.8 98.72 (1, 2, 10, 10, 3) 2 1 [312.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.084 0.973 (1, 6, 10, 10) 1 1 [3.084]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.306 (1, 1, 10, 10, 3) 1 1 [0.97]
- Total_time - 316.854 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.725 (1, 2, 10, 10, 3) 2 1 [311.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.058 0.968 (1, 6, 10, 10) 1 1 [3.058]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.306 (1, 1, 10, 10, 3) 1 1 [0.968]
+ Total_time - 315.826 - - - - -
@@ -394,10 +394,10 @@ 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 106.4 97.585 (1, 6, 10, 10, 1) 2 1 [106.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.781 1.633 (1, 6, 10, 10) 1 1 [1.781]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.852 0.782 (1, 3, 10, 10, 1) 1 1 [0.852]
- Total_time - 109.033 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 136.7 98.107 (1, 6, 10, 10, 1) 2 1 [136.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.789 1.284 (1, 6, 10, 10) 1 1 [1.789]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.848 0.609 (1, 3, 10, 10, 1) 1 1 [0.848]
+ Total_time - 139.338 - - - - -
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 6a7a19cf85..6966a1d90f 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/tmpkjphwqie/images/random'
+ '/tmp/tmp3j4lhnrq/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], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]
+ :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]
: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/tmpkjphwqie/images/target contains 8144 images
- /tmp/tmpkjphwqie/images/random contains 5000 images
+ /tmp/tmp3j4lhnrq/images/target contains 8144 images
+ /tmp/tmp3j4lhnrq/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 48s - loss: 0.2697 - accuracy: 0.9175 - val_loss: 0.1813 - val_accuracy: 0.9339 - 48s/epoch - 145ms/step
+ 328/328 - 47s - loss: 0.2245 - accuracy: 0.9235 - val_loss: 0.1260 - val_accuracy: 0.9611 - 47s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0998 - accuracy: 0.9648 - val_loss: 0.1298 - val_accuracy: 0.9581 - 44s/epoch - 134ms/step
+ 328/328 - 43s - loss: 0.0913 - accuracy: 0.9668 - val_loss: 0.1235 - val_accuracy: 0.9562 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0739 - accuracy: 0.9723 - val_loss: 0.1250 - val_accuracy: 0.9569 - 44s/epoch - 134ms/step
+ 328/328 - 43s - loss: 0.0568 - accuracy: 0.9792 - val_loss: 0.1212 - val_accuracy: 0.9653 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7fa9b2063d50>
+ <keras.callbacks.History object at 0x7f8a1c07cb10>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 10.519 seconds)
+ **Total running time of the script:** ( 4 minutes 20.175 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 4a3c3cf273..fa52ee18f6 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**06:14.259** total execution time for **how_to_work_with_microtvm** files:
+**05:22.212** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:10.519 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:20.175 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.518 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.965 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.371 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.262 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.849 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.808 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index ad958aa7ec..2a58704365 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.440** total execution time for **how_to_work_with_relay** files:
+**00:43.983** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.827 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.167 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.084 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.261 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.522 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.547 | 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 90cf186323..a90e554433 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 0x7fa953e9aef0>
+ <function my_cuda_math_rule at 0x7f8a1033d290>
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 5a3e332934..b05465ee99 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
=================
-**00:07.643** total execution time for **how_to_work_with_schedules** files:
+**00:07.684** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.310 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.206 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.017 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.116 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.565 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.595 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.564 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.113 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.047 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.046 | 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``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.016 | 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 d4992ef1e5..caac88b535 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjdextzae/input0.cc'\nsource_filename = \"/tmp/tmpjdextzae/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/tmp7s1v3uwk/input0.cc'\nsource_filename = \"/tmp/tmp7s1v3uwk/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 468b629786..2ff0beeb8c 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
=================
-**00:27.158** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.283** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.152 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.277 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 7159b8617c..6cd85b22a8 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 30.07s!
+ resnet18_v1 inference graph built in 29.02s!
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 f6094c3332..c757be5a03 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 19.88s!
+ yolov3-tiny inference graph built in 19.23s!
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 96789ed733..31f1d95689 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
=================
-**01:41.962** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.673** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.096 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.685 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.866 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.988 | 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 9f41bd0a06..c3f82d94a2 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
=================
-**00:03.161** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.163** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.712 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.701 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.449 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.462 | 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 7eee8f5594..69097ea441 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
=================
-**00:00.771** total execution time for **topic_vta_tutorials** files:
+**00:00.848** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.404 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.459 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.367 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.389 | 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 0f144cd216..058e1f572d 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 97.204 ms
+ Execution time of this operator: 96.208 ms
@@ -444,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.688 seconds)
+ **Total running time of the script:** ( 1 minutes 26.112 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 f423b95937..2cd529f640 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: 3.94/3.94 result: MeasureResult(costs=(0.0680505944,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.296668291091919, timestamp=1666866950.2135687) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
- No: 2 GFLOPS: 12.31/12.31 result: MeasureResult(costs=(0.021811631399999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5375258922576904, timestamp=1666866950.7758694) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
- No: 3 GFLOPS: 4.13/12.31 result: MeasureResult(costs=(0.0649240814,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1881957054138184, timestamp=1666866952.7357655) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
- No: 4 GFLOPS: 1.18/12.31 result: MeasureResult(costs=(0.2283630526,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7907021045684814, timestamp=1666866957.3120484) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
- No: 5 GFLOPS: 2.19/12.31 result: MeasureResult(costs=(0.1223811808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.114123821258545, timestamp=1666866959.5543363) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
- No: 6 GFLOPS: 1.89/12.31 result: MeasureResult(costs=(0.1419356216,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.421272039413452, timestamp=1666866962.7627308) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
- No: 7 GFLOPS: 4.24/12.31 result: MeasureResult(costs=(0.0632642322,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1744451522827148, timestamp=1666866963.9422517) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
- No: 8 GFLOPS: 3.43/12.31 result: MeasureResult(costs=(0.0782067068,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.448162317276001, timestamp=1666866965.4052196) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
- No: 9 GFLOPS: 0.51/12.31 result: MeasureResult(costs=(0.5260649714000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.524819374084473, timestamp=1666866974.273305) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
- No: 10 GFLOPS: 9.66/12.31 result: MeasureResult(costs=(0.027791939000000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.811206579208374, timestamp=1666866974.8884814) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+ No: 1 GFLOPS: 1.63/1.63 result: MeasureResult(costs=(0.1645176604,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.775430679321289, timestamp=1666899866.2928798) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+ No: 2 GFLOPS: 2.60/2.60 result: MeasureResult(costs=(0.1033720274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8303215503692627, timestamp=1666899868.1535747) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 3 GFLOPS: 12.23/12.23 result: MeasureResult(costs=(0.0219459878,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.49947690963745117, timestamp=1666899869.437013) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+ No: 4 GFLOPS: 1.82/12.23 result: MeasureResult(costs=(0.147590579,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.47967791557312, timestamp=1666899872.7191708) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
+ No: 5 GFLOPS: 3.06/12.23 result: MeasureResult(costs=(0.0877675978,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5474209785461426, timestamp=1666899874.4054992) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
+ No: 6 GFLOPS: 3.17/12.23 result: MeasureResult(costs=(0.0847982484,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5069401264190674, timestamp=1666899875.923931) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
+ No: 7 GFLOPS: 3.65/12.23 result: MeasureResult(costs=(0.0734906726,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3319902420043945, timestamp=1666899878.0177543) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+ No: 8 GFLOPS: 4.11/12.23 result: MeasureResult(costs=(0.06527137820000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2480006217956543, timestamp=1666899879.2697284) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
+ No: 9 GFLOPS: 3.90/12.23 result: MeasureResult(costs=(0.0687536636,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2471866607666016, timestamp=1666899880.6301255) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
+ No: 10 GFLOPS: 2.16/12.23 result: MeasureResult(costs=(0.124356304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1012117862701416, timestamp=1666899882.783746) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index cd21000fbf..1bd83fa47f 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': 517.6680545500018, 'median': 517.5069688999997, 'std': 2.239607076616047}
+ {'mean': 516.2649050599839, 'median': 516.4274659000057, 'std': 2.3130655123629618}
@@ -554,31 +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: 16.50/ 17.63 GFLOPS | Progress: (4/20) | 6.67 s
[Task 1/25] Current/Best: 18.97/ 18.97 GFLOPS | Progress: (8/20) | 10.32 s
[Task 1/25] Current/Best: 12.49/ 18.97 GFLOPS | Progress: (12/20) | 13.78 s
[Task 1/25] Current/Best: 21.63/ 23.04 GFLOPS | Progress: (16/20) | 15.39 s
[Task 1/25] Current/Best: 9.53/ 23.04 GFLOPS | Progress: (20/20) | 17.97 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 13.19/ 14.78 GFLOPS | Progress: (4/20) | 3.20 s
[Task 2/25] Current/Best: 12.90/ 14.78 GFLOPS | Progress: (8/20) | 5.03 s
[Task 2/25] Current/Best: 9.52/ 22.05 GFLOPS | Progress: (12/20) | 6.66 s
[Task 2/25] Current/Best: 12.01/ 22.05 GFLOPS | Progress: (16/20) | 7.97 s
[Task 2/25] Current/Best: 8.73/ 22.05 GFLOPS | Progress: (20/20) | 9.35 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.11/ 17.45 GFLOPS | Progress: (4/20) | 3.57 s
[Task 3/25] Current/Best: 7.98/ 22.18 GFLOPS | Progress: (8/20) | 5.64 s
[Task 3/25] Current/Best: 23.15/ 23.15 GFLOPS | Progress: (12/20) | 7.44 s
[Task 3/25] Current/Best: 19.11/ 23.15 GFLOPS | Progress: (16/20) | 9.03 s
[Task 3/25] Current/Best: 17.34/ 23.15 GFLOPS | Progress: (20/20) | 11.09 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 6.38/ 9.97 GFLOPS | Progress: (4/20) | 7.54 s
[Task 4/25] Current/Best: 4.58/ 17.01 GFLOPS | Progress: (8/20) | 9.25 s
[Task 4/25] Current/Best: 5.56/ 17.01 GFLOPS | Progress: (12/20) | 11.16 s
[Task 4/25] Current/Best: 13.05/ 19.90 GFLOPS | Progress: (16/20) | 13.11 s
[Task 4/25] Current/Best: 19.46/ 19.90 GFLOPS | Progress: (20/20) | 18.92 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 17.13/ 22.27 GFLOPS | Progress: (4/20) | 2.77 s
[Task 5/25] Current/Best: 2.83/ 22.27 GFLOPS | Progress: (8/20) | 5.03 s
[Task 5/25] Current/Best: 12.70/ 22.27 GFLOPS | Progress: (12/20) | 6.81 s
[Task 5/25] Current/Best: 16.73/ 22.27 GFLOPS | Progress: (16/20) | 8.46 s
[Task 5/25] Current/Best: 12.88/ 22.27 GFLOPS | Progress: (20/20) | 10.55 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 4.47/ 15.99 GFLOPS | Progress: (4/20) | 3.44 s
[Task 6/25] Current/Best: 17.66/ 17.66 GFLOPS | Progress: (8/20) | 5.37 s
[Task 6/25] Current/Best: 13.05/ 17.66 GFLOPS | Progress: (12/20) | 8.25 s
[Task 6/25] Current/Best: 3.94/ 17.66 GFLOPS | Progress: (16/20) | 11.17 s
[Task 6/25] Current/Best: 7.95/ 17.66 GFLOPS | Progress: (20/20) | 14.59 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.53/ 16.53 GFLOPS | Progress: (4/20) | 5.01 s
[Task 7/25] Current/Best: 12.82/ 19.08 GFLOPS | Progress: (8/20) | 7.11 s
[Task 7/25] Current/Best: 14.04/ 19.08 GFLOPS | Progress: (12/20) | 9.48 s
[Task 7/25] Current/Best: 11.26/ 19.08 GFLOPS | Progress: (16/20) | 12.05 s
[Task 7/25] Current/Best: 18.24/ 19.08 GFLOPS | Progress: (20/20) | 15.58 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.69/ 14.55 GFLOPS | Progress: (4/20) | 4.72 s
[Task 8/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (8/20) | 15.79 s
[Task 8/25] Current/Best: 5.56/ 18.94 GFLOPS | Progress: (12/20) | 19.10 s
[Task 8/25] Current/Best: 10.70/ 18.94 GFLOPS | Progress: (16/20) | 25.81 s
[Task 8/25] Current/Best: 19.43/ 19.43 GFLOPS | Progress: (20/20) | 27.81 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 5.76/ 23.19 GFLOPS | Progress: (4/20) | 3.46 s
[Task 9/25] Current/Best: 12.02/ 23.19 GFLOPS | Progress: (8/20) | 6.56 s
[Task 9/25] Current/Best: 14.41/ 23.19 GFLOPS | Progress: (12/20) | 9.10 s
[Task 9/25] Current/Best: 7.96/ 23.19 GFLOPS | Progress: (16/20) | 13.69 s
[Task 9/25] Current/Best: 16.68/ 23.19 GFLOPS | Progress: (20/20
) | 14.97 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.06/ 19.43 GFLOPS | Progress: (4/20) | 3.09 s
[Task 10/25] Current/Best: 12.08/ 19.43 GFLOPS | Progress: (8/20) | 7.24 s
[Task 10/25] Current/Best: 11.19/ 19.43 GFLOPS | Progress: (12/20) | 8.74 s
[Task 10/25] Current/Best: 5.87/ 19.43 GFLOPS | Progress: (16/20) | 10.35 s
[Task 10/25] Current/Best: 10.89/ 19.43 GFLOPS | Progress: (20/20) | 13.88 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 8.38/ 16.22 GFLOPS | Progress: (4/20) | 3.85 s
[Task 11/25] Current/Best: 6.70/ 23.90 GFLOPS | Progress: (8/20) | 6.60 s
[Task 11/25] Current/Best: 14.85/ 23.90 GFLOPS | Progress: (12/20) | 8.87 s
[Task 11/25] Current/Best: 16.08/ 23.90 GFLOPS | Progress: (16/20) | 10.94 s
[Task 11/25] Current/Best: 10.18/ 23.90 GFLOPS | Progress: (20/20) | 13.18 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.72/ 15.37 GFLOPS | Progress: (4/20) | 5.67 s
[Task 12/25] Current/Best: 16.62/ 16.62 GFLOPS | Progress: (8/20) | 8.80 s
[Task 12/25] Current/Best: 12.84/ 16.62 GFLOPS | Progress: (12/20) | 10.97 s
[Task 12/25] Current/Best: 15.38/ 17.02 GFLOPS | Progress: (16/20) | 16.93 s
[Task 12/25] Current/Best: 22.49/ 22.49 GFLOPS | Progress: (20/20) | 19.39 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.28/ 16.95 GFLOPS | Progress: (4/20) | 5.04 s
[Task 13/25] Current/Best: 17.85/ 17.85 GFLOPS | Progress: (8/20) | 8.89 s
[Task 13/25] Current/Best: 14.13/ 18.98 GFLOPS | Progress: (12/20) | 10.65 s
[Task 13/25] Current/Best: 15.22/ 18.98 GFLOPS | Progress: (16/20) | 13.01 s
[Task 13/25] Current/Best: 6.52/ 19.37 GFLOPS | Progress: (20/20) | 15.67 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 18.40/ 18.40 GFLOPS | Progress: (4/20) | 3.44 s
[Task 14/25] Current/Best: 13.43/ 18.78 GFLOPS | Progress: (8/20) | 5.51 s
[Task 14/25] Current/Best: 10.07/ 18.78 GFLOPS | Progress: (12/20) | 8.79 s
[Task 14/25] Current/Best: 11.98/ 18.78 GFLOPS | Progress: (16/20) | 17.60 s
[Task 14/25] Current/Best: 12.99/ 18.78 GFLOPS | Progress: (20/20) | 20.62 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: 12.64/ 13.44 GFLOPS | Progress: (4/20) | 9.21 s
[Task 1/25] Current/Best: 1.92/ 16.60 GFLOPS | Progress: (8/20) | 13.33 s
[Task 1/25] Current/Best: 7.15/ 17.69 GFLOPS | Progress: (12/20) | 17.09 s
[Task 1/25] Current/Best: 17.59/ 17.69 GFLOPS | Progress: (16/20) | 19.01 s
[Task 1/25] Current/Best: 21.90/ 23.12 GFLOPS | Progress: (20/20) | 20.96 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.73/ 17.28 GFLOPS | Progress: (4/20) | 2.69 s
[Task 2/25] Current/Best: 16.40/ 18.96 GFLOPS | Progress: (8/20) | 3.99 s
[Task 2/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (12/20) | 5.26 s
[Task 2/25] Current/Best: 13.63/ 19.01 GFLOPS | Progress: (16/20) | 6.89 s
[Task 2/25] Current/Best: 16.84/ 20.54 GFLOPS | Progress: (20/20) | 8.91 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 13.40/ 22.65 GFLOPS | Progress: (4/20) | 3.44 s
[Task 3/25] Current/Best: 6.37/ 22.65 GFLOPS | Progress: (8/20) | 6.20 s
[Task 3/25] Current/Best: 13.70/ 22.65 GFLOPS | Progress: (12/20) | 8.08 s
[Task 3/25] Current/Best: 20.72/ 22.65 GFLOPS | Progress: (16/20) | 10.09 s
[Task 3/25] Current/Best: 10.24/ 22.65 GFLOPS | Progress: (20/20) | 12.44 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.25/ 16.27 GFLOPS | Progress: (4/20) | 4.63 s
[Task 4/25] Current/Best: 11.64/ 16.27 GFLOPS | Progress: (8/20) | 9.53 s
[Task 4/25] Current/Best: 12.96/ 16.27 GFLOPS | Progress: (12/20) | 11.21 s
[Task 4/25] Current/Best: 3.33/ 16.27 GFLOPS | Progress: (16/20) | 13.18 s
[Task 4/25] Current/Best: 10.10/ 16.27 GFLOPS | Progress: (20/20) | 19.03 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.11/ 22.20 GFLOPS | Progress: (4/20) | 2.92 s
[Task 5/25] Current/Best: 14.70/ 22.20 GFLOPS | Progress: (8/20) | 4.51 s
[Task 5/25] Current/Best: 15.30/ 22.20 GFLOPS | Progress: (12/20) | 6.23 s
[Task 5/25] Current/Best: 15.85/ 22.20 GFLOPS | Progress: (16/20) | 8.53 s
[Task 5/25] Current/Best: 6.54/ 22.20 GFLOPS | Progress: (20/20) | 10.71 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 10.06/ 12.24 GFLOPS | Progress: (4/20) | 4.83 s
[Task 6/25] Current/Best: 12.91/ 12.91 GFLOPS | Progress: (8/20) | 7.92 s
[Task 6/25] Current/Best: 5.36/ 17.72 GFLOPS | Progress: (12/20) | 10.51 s
[Task 6/25] Current/Best: 12.27/ 17.72 GFLOPS | Progress: (16/20) | 14.86 s
[Task 6/25] Current/Best: 12.74/ 18.19 GFLOPS | Progress: (20/20) | 18.04 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 19.11/ 19.52 GFLOPS | Progress: (4/20) | 3.01 s
[Task 7/25] Current/Best: 11.38/ 19.52 GFLOPS | Progress: (8/20) | 6.07 s
[Task 7/25] Current/Best: 9.56/ 19.52 GFLOPS | Progress: (12/20) | 9.64 s
[Task 7/25] Current/Best: 8.70/ 19.52 GFLOPS | Progress: (16/20) | 11.77 s
[Task 7/25] Current/Best: 14.21/ 19.52 GFLOPS | Progress: (20/20) | 14.61 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.59/ 20.48 GFLOPS | Progress: (4/20) | 8.34 s
[Task 8/25] Current/Best: 3.35/ 20.48 GFLOPS | Progress: (8/20) | 11.25 s
[Task 8/25] Current/Best: 13.01/ 20.48 GFLOPS | Progress: (12/20) | 22.67 s
[Task 8/25] Current/Best: 13.39/ 20.48 GFLOPS | Progress: (16/20) | 26.95 s
[Task 8/25] Current/Best: 14.96/ 20.48 GFLOPS | Progress: (20/20) | 29.73 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 3.20/ 17.00 GFLOPS | Progress: (4/20) | 9.93 s
[Task 9/25] Current/Best: 16.43/ 17.00 GFLOPS | Progress: (8/20) | 12.85 s
[Task 9/25] Current/Best: 12.94/ 17.00 GFLOPS | Progress: (12/20) | 15.12 s
[Task 9/25] Current/Best: 10.24/ 17.00 GFLOPS | Progress: (16/20) | 18.69 s
[Task 9/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (20/
20) | 20.11 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 13.22/ 14.53 GFLOPS | Progress: (4/20) | 3.50 s
[Task 10/25] Current/Best: 5.62/ 19.73 GFLOPS | Progress: (8/20) | 4.93 s
[Task 10/25] Current/Best: 17.32/ 20.96 GFLOPS | Progress: (12/20) | 6.38 s
[Task 10/25] Current/Best: 5.71/ 20.96 GFLOPS | Progress: (16/20) | 8.25 s
[Task 10/25] Current/Best: 14.31/ 20.96 GFLOPS | Progress: (20/20) | 9.65 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.50/ 18.96 GFLOPS | Progress: (4/20) | 4.44 s
[Task 11/25] Current/Best: 6.88/ 21.53 GFLOPS | Progress: (8/20) | 6.69 s
[Task 11/25] Current/Best: 13.29/ 21.53 GFLOPS | Progress: (12/20) | 8.91 s
[Task 11/25] Current/Best: 15.82/ 21.68 GFLOPS | Progress: (16/20) | 11.00 s
[Task 11/25] Current/Best: 15.74/ 21.68 GFLOPS | Progress: (20/20) | 13.15 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 11.30/ 14.30 GFLOPS | Progress: (4/20) | 4.54 s
[Task 12/25] Current/Best: 13.17/ 14.30 GFLOPS | Progress: (8/20) | 7.18 s
[Task 12/25] Current/Best: 14.18/ 14.48 GFLOPS | Progress: (12/20) | 9.67 s
[Task 12/25] Current/Best: 14.25/ 14.48 GFLOPS | Progress: (16/20) | 16.07 s
[Task 12/25] Current/Best: 9.49/ 14.48 GFLOPS | Progress: (20/20) | 18.37 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 5.21/ 16.55 GFLOPS | Progress: (4/20) | 4.67 s
[Task 13/25] Current/Best: 21.70/ 21.70 GFLOPS | Progress: (8/20) | 6.48 s
[Task 13/25] Current/Best: 6.11/ 21.70 GFLOPS | Progress: (12/20) | 9.49 s
[Task 13/25] Current/Best: 16.10/ 21.70 GFLOPS | Progress: (16/20) | 12.63 s
[Task 13/25] Current/Best: 8.85/ 21.70 GFLOPS | Progress: (20/20) | 15.37 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 14.47/ 22.56 GFLOPS | Progress: (4/20) | 3.89 s
[Task 14/25] Current/Best: 9.09/ 22.56 GFLOPS | Progress: (8/20) | 9.26 s
[Task 14/25] Current/Best: 12.34/ 22.56 GFLOPS | Progress: (12/20) | 11.60 s
[Task 14/25] Current/Best: 12.96/ 22.56 GFLOPS | Progress: (16/20) | 14.73 s
[Task 14/25] Current/Best: 4.10/ 22.56 GFLOPS | Progress: (20/20) | 18.15 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 15/25] Current/Best: 15.58/ 20.74 GFLOPS | Progress: (4/20) | 7.25 s
[Task 15/25] Current/Best: 3.18/ 20.74 GFLOPS | Progress: (8/20) | 9.52 s
[Task 15/25] Current/Best: 16.97/ 20.74 GFLOPS | Progress: (12/20) | 11.20 s
[Task 15/25] Current/Best: 14.72/ 20.77 GFLOPS | Progress: (16/20) | 12.82 s
[Task 15/25] Current/Best: 18.64/ 20.77 GFLOPS | Progress: (20/20) | 14.76 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 8.07/ 11.80 GFLOPS | Progress: (4/20) | 4.03 s
[Task 16/25] Current/Best: 14.70/ 14.70 GFLOPS | Progress: (8/20) | 6.23 s
[Task 16/25] Current/Best: 9.84/ 14.70 GFLOPS | Progress: (12/20) | 9.06 s
[Task 16/25] Current/Best: 6.09/ 17.65 GFLOPS | Progress: (16/20) | 10.97 s
[Task 16/25] Current/Best: 12.93/ 17.65 GFLOPS | Progress: (20/20) | 12.47 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.56/ 22.54 GFLOPS | Progress: (4/20) | 3.57 s
[Task 17/25] Current/Best: 20.05/ 22.54 GFLOPS | Progress: (8/20) | 6.16 s
[Task 17/25] Current/Best: 12.71/ 22.54 GFLOPS | Progress: (12/20) | 8.08 s
[Task 17/25] Current/Best: 12.89/ 22.54 GFLOPS | Progress: (16/20) | 9.87 s
[Task 17/25] Current/Best: 11.70/ 22.54 GFLOPS | Progress: (20/20) | 12.84 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 12.24/ 16.89 GFLOPS | Progress: (4/20) | 4.64 s
[Task 18/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (8/20) | 6.84 s
[Task 18/25] Current/Best: 12.19/ 20.54 GFLOPS | Progress: (12/20) | 12.78 s
[Task 18/25] Current/Best: 10.75/ 20.54 GFLOPS | Progress: (16/20) | 15.83 s
[Task 18/25] Current/Best: 18.90/ 20.54 GFLOPS | Progress: (20/20) | 19.21 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 22.09/ 22.09 GFLOPS | Progress: (4/20) | 3.57 s
[Task 19/25] Current/Best: 9.05/ 22.09 GFLOPS | Progress: (8/20) | 6.71 s
[Task 19/25] Current/Best: 17.67/ 22.09 GFLOPS | Progress: (12/20) | 9.98 s
[Task 19/25] Current/Best: 3.09/ 22.09 GFLOPS | Progress: (16/20) | 13.58 s
[Task 19/25] Current/Best: 17.89/ 22.09 GFLOPS | Progress: (20/20) | 15.72 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 16.56/ 16.56 GFLOPS | Progress: (4/20) | 3.49 s
[Task 20/25] Current/Best: 10.02/ 16.56 GFLOPS | Progress: (8/20) | 8.05 s
[Task 20/25] Current/Best: 10.69/ 16.56 GFLOPS | Progress: (12/20) | 11.07 s
[Task 20/25] Current/Best: 11.34/ 17.43 GFLOPS | Progress: (16/20) | 14.67 s
[Task 20/25] Current/Best: 5.27/ 17.43 GFLOPS | Progress: (20/20) | 18.00 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 7.83/ 18.05 GFLOPS | Progress: (4/20) | 3.76 s
[Task 21/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (8/20) | 4.86 s
[Task 21/25] Current/Best: 8.76/ 18.26 GFLOPS | Progress: (12/20) | 8.49 s Done.
+
[Task 15/25] Current/Best: 14.66/ 22.12 GFLOPS | Progress: (4/20) | 6.32 s
[Task 15/25] Current/Best: 13.11/ 22.12 GFLOPS | Progress: (8/20) | 8.10 s
[Task 15/25] Current/Best: 15.53/ 22.12 GFLOPS | Progress: (12/20) | 9.56 s
[Task 15/25] Current/Best: 10.55/ 22.12 GFLOPS | Progress: (16/20) | 13.34 s
[Task 15/25] Current/Best: 19.95/ 22.12 GFLOPS | Progress: (20/20) | 17.51 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 16.03/ 16.13 GFLOPS | Progress: (4/20) | 4.11 s
[Task 16/25] Current/Best: 9.33/ 16.13 GFLOPS | Progress: (8/20) | 7.18 s
[Task 16/25] Current/Best: 17.03/ 17.42 GFLOPS | Progress: (12/20) | 10.19 s
[Task 16/25] Current/Best: 18.74/ 18.74 GFLOPS | Progress: (16/20) | 12.15 s
[Task 16/25] Current/Best: 6.26/ 19.04 GFLOPS | Progress: (20/20) | 13.39 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.35/ 17.50 GFLOPS | Progress: (4/20) | 3.56 s
[Task 17/25] Current/Best: 13.21/ 17.50 GFLOPS | Progress: (8/20) | 7.51 s
[Task 17/25] Current/Best: 14.45/ 17.64 GFLOPS | Progress: (12/20) | 9.58 s
[Task 17/25] Current/Best: 23.94/ 23.94 GFLOPS | Progress: (16/20) | 12.01 s
[Task 17/25] Current/Best: 11.73/ 23.94 GFLOPS | Progress: (20/20) | 14.72 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 9.60/ 18.66 GFLOPS | Progress: (4/20) | 3.48 s
[Task 18/25] Current/Best: 9.90/ 18.66 GFLOPS | Progress: (8/20) | 8.29 s
[Task 18/25] Current/Best: 10.36/ 18.78 GFLOPS | Progress: (12/20) | 13.71 s
[Task 18/25] Current/Best: 20.09/ 20.09 GFLOPS | Progress: (16/20) | 15.36 s
[Task 18/25] Current/Best: 11.23/ 20.09 GFLOPS | Progress: (20/20) | 18.64 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 3.09/ 17.78 GFLOPS | Progress: (4/20) | 4.20 s
[Task 19/25] Current/Best: 22.63/ 22.63 GFLOPS | Progress: (8/20) | 8.39 s
[Task 19/25] Current/Best: 6.68/ 22.63 GFLOPS | Progress: (12/20) | 10.96 s
[Task 19/25] Current/Best: 20.29/ 22.63 GFLOPS | Progress: (16/20) | 13.65 s
[Task 19/25] Current/Best: 17.86/ 22.63 GFLOPS | Progress: (20/20) | 16.83 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 11.14/ 19.13 GFLOPS | Progress: (4/20) | 3.37 s
[Task 20/25] Current/Best: 12.93/ 19.13 GFLOPS | Progress: (8/20) | 5.15 s
[Task 20/25] Current/Best: 8.49/ 19.13 GFLOPS | Progress: (12/20) | 11.32 s
[Task 20/25] Current/Best: 2.25/ 20.28 GFLOPS | Progress: (16/20) | 14.81 s
[Task 20/25] Current/Best: 9.60/ 20.28 GFLOPS | Progress: (20/20) | 17.22 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 17.98/ 18.89 GFLOPS | Progress: (4/20) | 2.54 s
[Task 21/25] Current/Best: 9.57/ 18.89 GFLOPS | Progress: (8/20) | 5.72 s
[Task 21/25] Current/Best: 8.45/ 18.89 GFLOPS | Progress: (12/20) | 10.18 s
[Task 21/25] Current/Best: 17.06/ 18.89 GFLOPS | Progress: (16/20) | 11.64 s
[Task 21/25] Current/Best: 8.95/ 18.89 GFLOPS | Progress: (20/20
) | 13.54 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 14.11/ 21.67 GFLOPS | Progress: (4/20) | 3.88 s
[Task 22/25] Current/Best: 14.54/ 21.67 GFLOPS | Progress: (8/20) | 6.92 s
[Task 22/25] Current/Best: 5.50/ 21.67 GFLOPS | Progress: (12/20) | 8.42 s
[Task 22/25] Current/Best: 6.47/ 21.67 GFLOPS | Progress: (16/20) | 13.83 s
[Task 22/25] Current/Best: 6.81/ 21.67 GFLOPS | Progress: (20/20) | 16.31 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 2.65/ 10.66 GFLOPS | Progress: (4/20) | 5.35 s
[Task 23/25] Current/Best: 10.89/ 12.96 GFLOPS | Progress: (8/20) | 8.80 s
[Task 23/25] Current/Best: 10.69/ 19.27 GFLOPS | Progress: (12/20) | 11.86 s
[Task 23/25] Current/Best: 17.51/ 22.32 GFLOPS | Progress: (16/20) | 14.29 s
[Task 23/25] Current/Best: 17.62/ 22.32 GFLOPS | Progress: (20/20) | 16.56 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.96/ 8.78 GFLOPS | Progress: (4/20) | 12.30 s Done.
Done.
-
[Task 21/25] Current/Best: 17.53/ 18.26 GFLOPS | Progress: (16/20) | 10.58 s
[Task 21/25] Current/Best: 11.40/ 18.26 GFLOPS | Progress: (20/20) | 11.92 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 16.42/ 20.57 GFLOPS | Progress: (4/20) | 3.55 s
[Task 22/25] Current/Best: 9.19/ 20.57 GFLOPS | Progress: (8/20) | 5.02 s
[Task 22/25] Current/Best: 2.69/ 20.57 GFLOPS | Progress: (12/20) | 6.98 s
[Task 22/25] Current/Best: 8.15/ 20.57 GFLOPS | Progress: (16/20) | 8.46 s
[Task 22/25] Current/Best: 7.40/ 20.57 GFLOPS | Progress: (20/20) | 10.02 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.54/ 14.75 GFLOPS | Progress: (4/20) | 5.27 s
[Task 23/25] Current/Best: 10.00/ 21.95 GFLOPS | Progress: (8/20) | 7.27 s
[Task 23/25] Current/Best: 9.65/ 21.95 GFLOPS | Progress: (12/20) | 10.15 s
[Task 23/25] Current/Best: 12.89/ 21.95 GFLOPS | Progress: (16/20) | 12.49 s
[Task 23/25] Current/Best: 16.28/ 22.65 GFLOPS | Progress: (20/20) | 14.44 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.54/ 8.81 GFLOPS | Progress: (4/20) | 12.09 s
[Task 24/25] Current/Best: 4.26/ 8.81 GFLOPS | Progress: (8/20) | 23.78 s
[Task 24/25] Current/Best: 9.89/ 9.89 GFLOPS | Progress: (12/20) | 30.49 s
[Task 24/25] Current/Best: 3.54/ 9.89 GFLOPS | Progress: (16/20) | 34.78 s
[Task 24/25] Current/Best: 2.97/ 9.89 GFLOPS | Progress: (20/20) | 37.12 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 25/25] Current/Best: 7.44/ 8.57 GFLOPS | Progress: (4/20) | 12.26 s
[Task 25/25] Current/Best: 4.85/ 8.57 GFLOPS | Progress: (8/20) | 23.54 s
[Task 25/25] Current/Best: 5.26/ 9.54 GFLOPS | Progress: (12/20) | 35.13 s
[Task 25/25] Current/Best: 8.48/ 9.54 GFLOPS | Progress: (16/20) | 37.44 s
[Task 25/25] Current/Best: 5.70/ 9.54 GFLOPS | Progress: (20/20) | 48.19 s
+
[Task 24/25] Current/Best: 3.09/ 8.78 GFLOPS | Progress: (8/20) | 24.16 s
[Task 24/25] Current/Best: 3.77/ 8.78 GFLOPS | Progress: (12/20) | 26.78 s
[Task 24/25] Current/Best: 6.51/ 10.23 GFLOPS | Progress: (16/20) | 33.47 s
[Task 24/25] Current/Best: 9.21/ 10.23 GFLOPS | Progress: (20/20) | 44.18 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 9.26 GFLOPS | Progress: (4/20) | 13.01 s
[Task 25/25] Current/Best: 3.01/ 9.26 GFLOPS | Progress: (8/20) | 14.82 s
[Task 25/25] Current/Best: 5.41/ 9.26 GFLOPS | Progress: (12/20) | 15.96 s
[Task 25/25] Current/Best: 2.91/ 9.26 GFLOPS | Progress: (16/20) | 26.65 s
[Task 25/25] Current/Best: 6.36/ 9.36 GFLOPS | Progress: (20/20) | 30.99 s Done.
+
@@ -674,8 +674,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621103
- class='n02123159 tiger cat' with probability=0.356379
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 421.82080812000095, 'median': 420.72292930000685, 'std': 2.864997551003513}
- unoptimized: {'mean': 517.6680545500018, 'median': 517.5069688999997, 'std': 2.239607076616047}
+ optimized: {'mean': 412.1639453500211, 'median': 411.27183655003137, 'std': 2.848139501968217}
+ unoptimized: {'mean': 516.2649050599839, 'median': 516.4274659000057, 'std': 2.3130655123629618}
@@ -756,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 48.633 seconds)
+ **Total running time of the script:** ( 10 minutes 57.187 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 65a5e9be37..e7574f80c6 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
- 1.302e-07 secs/op
+ 1.268e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 8f5c677ddc..aa4c7302ec 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xe5a19a0)), stage(b, placeholder(b, 0x5ed9210)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
+ [stage(a, placeholder(a, 0x23bbda40)), stage(b, placeholder(b, 0x213b4a70)), 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 cdaadc661f..5fcfabcbdd 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
=================
-**14:17.415** total execution time for **tutorial** files:
+**14:25.291** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:48.633 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:57.187 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:18.688 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:26.112 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.066 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.529 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.072 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.486 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:29.813 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.244 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.237 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.796 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.745 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.739 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.151 | 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``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+| :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_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 816ca4f7ce..1935733904 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: 0.000007
- naive: 0.000009
+ Numpy running time: 0.000008
+ naive: 0.000007
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000009
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.555360000675137e-06 1.0
- naive 8.9559e-06 1.3661949914387055
- parallel 7.5355e-06 1.1495173414158673
- vector 2.4596199999999997e-05 3.752074637772271
+ numpy 7.828130001144019e-06 1.0
+ naive 6.9914000000000005e-06 0.8931124034703388
+ parallel 9.033399999999999e-06 1.1539665282359695
+ vector 2.45923e-05 3.141529330300599
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018763
+ Numpy running time: 0.018316
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.464069
+ none: 3.418990
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.310746
+ blocking: 0.307668
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.353294
+ vectorization: 0.348105
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118008
+ loop permutation: 0.125197
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.107706
+ array packing: 0.109678
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110762
+ block caching: 0.111369
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146763
+ parallelization: 0.147371
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4640688141 1.0
- blocking 0.3107459428 0.08970547626974175
- vectorization 0.3532940843 0.10198818304704763
- loop permutation 0.11800828 0.03406637868152736
- array packing 0.10770599039999999 0.031092335683863454
- block caching 0.1107623365 0.03197463516000538
- parallelization 0.1467633535 0.04236733199485548
+ none 3.4189896815 1.0
+ blocking 0.30766777419999997 0.08998792124608522
+ vectorization 0.348104966 0.10181515547811694
+ loop permutation 0.12519716390000002 0.036618175415221714
+ array packing 0.10967809879999998 0.03207909617085517
+ block caching 0.1113691896 0.03257371328220547
+ parallelization 0.14737074339999998 0.043103594081437706
@@ -1663,7 +1663,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.066 seconds)
+ **Total running time of the script:** ( 1 minutes 1.529 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 8c5437c1cb..708f451a53 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-5c9066d816408bd2858c9758b0865ca08112c78f
+5acf3f90c63b6760cd23796b442f8ac20e645af0
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index f7b2aceefb..fbd7d8508e 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 11.923 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.135 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_keras.html b/docs/how_to/compile_models/from_keras.html
index 2b1ee9bba2..44c51db793 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 967ms/step
+1/1 [==============================] - 1s 960ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 823c3c48be..7c56662c73 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.zip2ac2aad8-5672-4203-94d1-13b04497c543 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.zip4d6e2683-624a-4385-a42e-aae535fa608c 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 055afc96a4..50af359658 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,13 +448,11 @@ 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, 37.3MB/s]
- 38%|###7 | 15.7M/41.5M [00:00<00:00, 54.2MB/s]
- 52%|#####2 | 21.7M/41.5M [00:00<00:00, 53.7MB/s]
- 66%|######5 | 27.3M/41.5M [00:00<00:00, 47.3MB/s]
- 77%|#######7 | 32.1M/41.5M [00:00<00:00, 47.4MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 44.9MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 46.9MB/s]
+ 25%|##5 | 10.4M/41.5M [00:00<00:00, 109MB/s]
+ 50%|##### | 20.8M/41.5M [00:00<00:00, 87.8MB/s]
+ 71%|####### | 29.4M/41.5M [00:00<00:00, 75.2MB/s]
+ 89%|########8 | 36.8M/41.5M [00:00<00:00, 70.5MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 64.9MB/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 25ad4574ae..93da39ad77 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,10 +431,11 @@ 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]
- 31%|###1 | 14.0M/44.7M [00:00<00:00, 147MB/s]
- 63%|######3 | 28.2M/44.7M [00:00<00:00, 148MB/s]
- 95%|#########4| 42.3M/44.7M [00:00<00:00, 99.8MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 112MB/s]
+ 18%|#7 | 8.01M/44.7M [00:00<00:00, 83.8MB/s]
+ 45%|####4 | 20.0M/44.7M [00:00<00:00, 109MB/s]
+ 68%|######8 | 30.4M/44.7M [00:00<00:00, 109MB/s]
+ 91%|#########1| 40.8M/44.7M [00:00<00:00, 103MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/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 797b13f593..c5746798da 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 11.647 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.534 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 97b2ac89c3..6444536e1e 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>05:46.095</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:45.975</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -348,44 +348,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:11.923</p></td>
+<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>01:11.534</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:11.647</p></td>
+<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>01:11.135</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>00:46.026</p></td>
+<td><p>00:46.380</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>00:31.977</p></td>
+<td><p>00:32.801</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>00:30.268</p></td>
+<td><p>00:29.876</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>00:26.618</p></td>
+<td><p>00:26.603</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>00:24.981</p></td>
+<td><p>00:25.146</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>00:22.980</p></td>
+<td><p>00:22.723</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>00:17.318</p></td>
+<td><p>00:17.386</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>00:02.357</p></td>
+<td><p>00:02.391</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index a2b87c2760..c5a47b3ded 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.5495 16.7429 17.0968 15.7640 0.4404
+ 15.8826 15.8755 16.0334 15.7582 0.0801
</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 5c53e90809..db5c328548 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,25 +453,27 @@ 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%|5 | 9.21M/170M [00:00<00:01, 96.6MB/s]
- 11%|# | 18.4M/170M [00:00<00:02, 73.6MB/s]
- 15%|#5 | 25.8M/170M [00:00<00:02, 71.2MB/s]
- 19%|#9 | 32.7M/170M [00:00<00:02, 66.2MB/s]
- 25%|##4 | 42.1M/170M [00:00<00:01, 72.2MB/s]
- 30%|##9 | 50.4M/170M [00:00<00:01, 76.3MB/s]
- 36%|###6 | 61.8M/170M [00:00<00:01, 88.9MB/s]
- 42%|####2 | 72.0M/170M [00:00<00:01, 93.3MB/s]
- 48%|####7 | 81.4M/170M [00:01<00:00, 94.7MB/s]
- 53%|#####3 | 90.7M/170M [00:01<00:00, 95.5MB/s]
- 59%|#####8 | 99.9M/170M [00:01<00:00, 91.9MB/s]
- 66%|######5 | 111M/170M [00:01<00:00, 100MB/s]
- 71%|#######1 | 121M/170M [00:01<00:00, 86.1MB/s]
- 76%|#######6 | 130M/170M [00:01<00:00, 83.3MB/s]
- 81%|########1 | 138M/170M [00:01<00:00, 85.2MB/s]
- 86%|########6 | 147M/170M [00:01<00:00, 85.1MB/s]
- 92%|#########2| 157M/170M [00:01<00:00, 91.8MB/s]
- 98%|#########7| 166M/170M [00:02<00:00, 92.0MB/s]
-100%|##########| 170M/170M [00:02<00:00, 87.5MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 70.6MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 73.8MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:02, 75.5MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:02, 65.1MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:02, 65.7MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:02, 56.5MB/s]
+ 33%|###3 | 56.3M/170M [00:00<00:01, 64.0MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:01, 66.7MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:01, 71.1MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 70.4MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:01, 71.4MB/s]
+ 57%|#####6 | 96.0M/170M [00:01<00:01, 72.2MB/s]
+ 61%|######1 | 104M/170M [00:01<00:00, 71.1MB/s]
+ 66%|######5 | 112M/170M [00:01<00:00, 64.4MB/s]
+ 71%|####### | 120M/170M [00:01<00:00, 68.1MB/s]
+ 75%|#######5 | 128M/170M [00:01<00:00, 71.2MB/s]
+ 81%|######## | 137M/170M [00:02<00:00, 78.0MB/s]
+ 85%|########5 | 145M/170M [00:02<00:00, 76.6MB/s]
+ 92%|#########1| 156M/170M [00:02<00:00, 87.3MB/s]
+ 97%|#########6| 164M/170M [00:02<00:00, 81.2MB/s]
+100%|##########| 170M/170M [00:02<00:00, 73.2MB/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=& [...]
@@ -569,7 +571,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 16.545 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 16.979 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 094bc90361..bdff67c66c 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, 48.2MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 73.0MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 71.8MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 101MB/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)
- 90.5043 90.2555 105.2862 89.9734 1.5511
+ 90.2623 90.2032 90.8305 89.9470 0.1946
</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 5.984 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.915 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 b0496412c5..b7dc66f414 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)
- 120.3099 120.2600 125.4839 119.3358 0.7139
+ 120.9118 120.9551 121.7318 119.8852 0.3764
</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 31.372 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 29.342 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 0b82a0a004..6fdb6bcf47 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 27.332 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.368 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 dcaa4e7f7a..ba7f7926da 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]
- 1%|1 | 1405/132723 [00:00<00:09, 13936.64KB/s]
- 3%|2 | 3869/132723 [00:00<00:06, 19965.20KB/s]
- 6%|6 | 7965/132723 [00:00<00:04, 29404.06KB/s]
- 11%|#1 | 14695/132723 [00:00<00:02, 44265.33KB/s]
- 18%|#7 | 23357/132723 [00:00<00:01, 59473.39KB/s]
- 24%|##4 | 32061/132723 [00:00<00:01, 68816.74KB/s]
- 31%|### | 40767/132723 [00:00<00:01, 74767.77KB/s]
- 37%|###7 | 49488/132723 [00:00<00:01, 78720.54KB/s]
- 44%|####3 | 58220/132723 [00:00<00:00, 81404.13KB/s]
- 51%|##### | 67053/132723 [00:01<00:00, 83533.09KB/s]
- 57%|#####7 | 75861/132723 [00:01<00:00, 84920.44KB/s]
- 64%|######3 | 84416/132723 [00:01<00:00, 85109.63KB/s]
- 70%|####### | 93221/132723 [00:01<00:00, 85998.33KB/s]
- 77%|#######6 | 102097/132723 [00:01<00:00, 86830.83KB/s]
- 84%|########3 | 110909/132723 [00:01<00:00, 87212.87KB/s]
- 90%|######### | 119714/132723 [00:01<00:00, 87461.44KB/s]
- 97%|#########6| 128560/132723 [00:01<00:00, 87758.54KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75713.63KB/s]
+ 1%|1 | 1784/132723 [00:00<00:07, 17564.22KB/s]
+ 4%|3 | 5256/132723 [00:00<00:04, 27552.80KB/s]
+ 9%|8 | 11765/132723 [00:00<00:02, 44619.12KB/s]
+ 15%|#5 | 20185/132723 [00:00<00:01, 60201.27KB/s]
+ 22%|##1 | 28566/132723 [00:00<00:01, 68697.86KB/s]
+ 28%|##7 | 37096/132723 [00:00<00:01, 74330.63KB/s]
+ 34%|###4 | 45630/132723 [00:00<00:01, 77925.59KB/s]
+ 41%|#### | 54182/132723 [00:00<00:00, 80338.64KB/s]
+ 47%|####7 | 62772/132723 [00:00<00:00, 82074.61KB/s]
+ 54%|#####3 | 71320/132723 [00:01<00:00, 83123.61KB/s]
+ 60%|###### | 79936/132723 [00:01<00:00, 84050.20KB/s]
+ 67%|######6 | 88493/132723 [00:01<00:00, 84507.09KB/s]
+ 73%|#######3 | 96945/132723 [00:01<00:00, 84158.72KB/s]
+ 79%|#######9 | 105469/132723 [00:01<00:00, 84481.26KB/s]
+ 86%|########5 | 113918/132723 [00:01<00:00, 84392.95KB/s]
+ 92%|#########2| 122469/132723 [00:01<00:00, 84724.32KB/s]
+ 99%|#########8| 131015/132723 [00:01<00:00, 84943.87KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 76895.56KB/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> ( 2 minutes 58.330 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 57.204 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 c1aa9f40e2..0b0d13d544 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>12:46.106</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:41.628</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:16.545</p></td>
+<td><p>03:16.979</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:58.330</p></td>
+<td><p>02:57.204</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>02:31.372</p></td>
+<td><p>02:29.342</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>01:27.332</p></td>
+<td><p>01:26.368</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>01:05.984</p></td>
+<td><p>01:04.915</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:35.724</p></td>
+<td><p>00:35.620</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.490</p></td>
+<td><p>00:25.659</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:25.322</p></td>
+<td><p>00:25.534</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index f07e16e702..a07775aace 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.zipbca5da70-3120-40a7-b5d7-1ba9ea749349 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.zip7f87b484-f896-4e08-8ee7-ce074ed2f7fa 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 91e0326187..fe2c7867b6 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>00:46.920</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:48.028</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>00:43.378</p></td>
+<td><p>00:44.613</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>00:02.457</p></td>
+<td><p>00:02.391</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>00:01.076</p></td>
+<td><p>00:01.014</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 e55a980ca5..cd8162a81c 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: 6878us [6878us] (46.00%; 46.00%)
-FoldScaleAxis: 8074us [6us] (54.00%; 54.00%)
- FoldConstant: 8068us [1752us] (53.96%; 99.92%)
- InferType: 6316us [6316us] (42.24%; 78.28%)
+InferType: 6694us [6694us] (46.71%; 46.71%)
+FoldScaleAxis: 7638us [5us] (53.29%; 53.29%)
+ FoldConstant: 7633us [1528us] (53.26%; 99.93%)
+ InferType: 6105us [6105us] (42.60%; 79.98%)
</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: 6312us [6312us] (44.47%; 44.47%)
-FoldScaleAxis: 7880us [5us] (55.53%; 55.53%)
- FoldConstant: 7875us [1704us] (55.49%; 99.94%)
- InferType: 6171us [6171us] (43.48%; 78.36%)
+InferType: 6110us [6110us] (44.75%; 44.75%)
+FoldScaleAxis: 7545us [5us] (55.25%; 55.25%)
+ FoldConstant: 7540us [1528us] (55.22%; 99.94%)
+ InferType: 6013us [6013us] (44.03%; 79.74%)
</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 402b586eff..567182f7d3 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: 54.258209 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 39.235359 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 5d38a4d55e..43b070d2df 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -916,7 +916,7 @@ 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: 11.481488 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.416918 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 79d1e4a8ad..8bf792b3fa 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: 0.018914
-Baseline: 3.350183
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019147
+Baseline: 3.365475
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -535,7 +535,7 @@ 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: 0.317286
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.308592
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -602,7 +602,7 @@ 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: 0.346113
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.349700
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -663,7 +663,7 @@ 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: 0.119121
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.127762
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -746,7 +746,7 @@ 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: 0.110715
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110178
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -832,7 +832,7 @@ 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: 0.111440
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111495
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -922,7 +922,7 @@ 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: 0.147520
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147570
</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 0b1173d200..d7458636e1 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>00:35.043</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.285</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>00:32.546</p></td>
+<td><p>00:32.688</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>00:01.387</p></td>
+<td><p>00:01.440</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>00:01.111</p></td>
+<td><p>00:01.157</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 303af6aa4b..7df8c15b75 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>08:23.741</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:27.418</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>04:57.188</p></td>
+<td><p>05:02.010</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>01:33.267</p></td>
+<td><p>01:32.568</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>01:03.571</p></td>
+<td><p>01:02.662</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>00:26.479</p></td>
+<td><p>00:27.365</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>00:12.063</p></td>
+<td><p>00:11.728</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>00:11.174</p></td>
+<td><p>00:11.086</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 8e98106490..4b533c819d 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
@@ -504,105 +504,346 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), 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" = 49 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 128) {
- let cse_var_1: int32 = (rc.outer.outer*36)
+ 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)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_1 < 36), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[(threadIdx.x_1*9)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*9) + 1)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 2)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 6)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 3)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 5)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 4)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 4)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 5)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 3)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 6)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 2)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 7)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*196) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 1)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 8)] = 0f32
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*48)] = @tir.if_then_else((((3 <= floormod((threadIdx.x_1*16), 27)) && (floormod((threadIdx.x_1*48), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 27)*49)) + (floordiv(floormod((threadIdx.x_1*16), 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 1)] = @tir.if_then_else(((3 <= floormod((threadIdx.x_1*16), 27)) && (floormod(((threadIdx.x_1*48) + 1), 81) < 72)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 27)*49)) + (floordiv(floormod((threadIdx.x_1*16), 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2)] = @tir.if_then_else((((3 <= floormod((threadIdx.x_1*16), 27)) && (floormod(((threadIdx.x_1*48) + 2), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 27)*49)) + (floordiv(floormod((threadIdx.x_1*16), 27), 3)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 9)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 9), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 10)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 10), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 11)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 11), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 12)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 4), 27)) && (floormod(((threadIdx.x_1*48) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 13)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 4), 27)) && (floormod(((threadIdx.x_1*48) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 14)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 4), 27)) && (floormod(((threadIdx.x_1*48) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 15)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 16)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 17)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 18)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 18), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 19)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 19), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 20)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 20), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 21)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 22)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 23)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 24)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 25)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 26)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 26), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 27)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 27), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 28)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 28), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 29)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 29), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 30)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 30), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 31)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 31), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 32)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 32), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 33)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 33), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 34)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 34), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 35)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 35), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 36)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 37)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 37), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 38)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 38), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 39)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 39), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 40)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 40), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 41)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 41), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 42)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 42), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 43)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 44)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 44), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*48) + 45)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 45), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 46)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 46), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*48) + 47)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 47), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 98), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 26), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 294), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 6), 36), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 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" = 98;
- if @tir.likely((threadIdx.x_2 < 86), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 490), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 22), 36), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2352)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, dt [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2353)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, dt [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2354)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 1), 27)) && (floormod(((threadIdx.x_1*48) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, dt [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2355)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dt [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2356)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dt [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2357)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 2), 27)) && (floormod(((threadIdx.x_1*48) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dt [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2358)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 9), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 786), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2359)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 10), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 786), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2360)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 11), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 786), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 1), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2361)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 787), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1* [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2362)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 787), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1* [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2363)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)) && (floormod(((threadIdx.x_1*48) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 787), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1* [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2364)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 788), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2365)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 788), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2366)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 5), 27)) && (floormod(((threadIdx.x_1*48) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 788), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2367)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 18), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 789), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2368)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 19), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 789), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2369)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)) && (floormod(((threadIdx.x_1*48) + 20), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 789), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 2), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2370)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 790), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2371)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 790), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2372)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 7), 27)) && (floormod(((threadIdx.x_1*48) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 790), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2373)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 791), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2374)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 791), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2375)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 8), 27)) && (floormod(((threadIdx.x_1*48) + 26), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 791), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, d [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2376)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 27), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 792), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2377)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 28), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 792), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2378)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)) && (floormod(((threadIdx.x_1*48) + 29), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 792), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 3), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2379)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 30), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 793), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2380)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 31), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 793), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2381)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 10), 27)) && (floormod(((threadIdx.x_1*48) + 32), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 793), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2382)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 33), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 794), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2383)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 34), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 794), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2384)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 11), 27)) && (floormod(((threadIdx.x_1*48) + 35), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 794), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2385)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 795), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2386)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 37), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 795), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2387)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)) && (floormod(((threadIdx.x_1*48) + 38), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 795), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 4), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2388)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 39), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 796), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2389)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 40), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 796), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2390)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 13), 27)) && (floormod(((threadIdx.x_1*48) + 41), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 796), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2391)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 42), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 797), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2392)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 797), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2393)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 14), 27)) && (floormod(((threadIdx.x_1*48) + 44), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 797), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2394)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 45), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 3))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 798), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2395)] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 46), 81) < 72)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 798), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2396)] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)) && (floormod(((threadIdx.x_1*48) + 47), 81) < 72)) && (floormod(threadIdx.x_1, 3) < 2)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 798), 27)*49)) + (floormod((floordiv((threadIdx.x_1*16), 3) + 5), 9)*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2397)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 16), 27)) && (floormod(((threadIdx.x_1*48) + 48), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 3), 9))) && (floormod(((threadIdx.x_1*3) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 799), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 3), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2398)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 16), 27)) && (floormod(((threadIdx.x_1*48) + 49), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 4), 9))) && (floormod(((threadIdx.x_1*3) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 799), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 4), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 5), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*48) + 2399)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*16) + 16), 27)) && (floormod(((threadIdx.x_1*48) + 50), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*3) + 5), 9))) && (floormod(((threadIdx.x_1*3) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 799), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 16), 27), 3)*7)) + floormod(((threadIdx.x_1*3) + 5), 9)) - 8)], 0f32, [...]
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*18432) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 49), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 98), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((blockIdx.x*18432) + cse_var_1) + threadIdx.x_2) + 147)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 196), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 245), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 245), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 294), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 343), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 55), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*18432) + (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" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 441), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 51)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 490), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 202), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 539), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 251), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 588), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 637), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 61), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 686), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 735), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 53)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*18432) + (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" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 833)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 833), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 257), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 882), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 6)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 931)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 931), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 67), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 980), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 1029)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 1029), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 55)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 1078), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 214), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_2 < 25), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1127)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 1127), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 263), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
}
- for (rc.outer.inner: int32, 0, 2) {
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 288)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 324)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 289)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 325)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 290)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 326)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 297)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 333)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 298)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 334)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 299)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 335)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 360)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 108)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 396)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 73)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 361)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 109)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 397)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 74)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 362)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 110)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 398)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 81)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 369)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 117)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 405)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 82)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 370)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 118)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 406)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 83)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 371)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 119)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + 407)]))
+ for (rc.outer.inner: int32, 0, 16) {
+ let cse_var_3: int32 = (rc.outer.inner*18)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_3]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 288)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 576)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 864)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 289)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 577)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 865)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 290)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 578)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 866)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 291)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 579)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 867)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 292)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 580)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 868)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 293)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 581)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 869)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 294)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 582)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 870)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 295)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 583)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 871)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 296)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 584)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 872)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 297)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(cse_var_3 + 873)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 298)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 586)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(cse_var_3 + 874)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 299)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 587)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(cse_var_3 + 875)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 300)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 588)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(cse_var_3 + 876)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 301)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 589)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(cse_var_3 + 877)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 302)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 590)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(cse_var_3 + 878)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 303)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 591)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(cse_var_3 + 879)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 304)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 592)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(cse_var_3 + 880)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 305)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 593)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(cse_var_3 + 881)]))
}
}
}
}
for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 8)]), 0f32)
+ compute[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*4) + i1.inner)]), 0f32)
}
}
}
@@ -639,7 +880,7 @@ 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: 0.275 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.335 ms
</pre></div>
</div>
</div>
@@ -668,10 +909,10 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
@@ -681,9 +922,9 @@ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+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_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
@@ -691,8 +932,8 @@ compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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)
@@ -717,14 +958,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=9)
+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=48)
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=98)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -742,96 +983,312 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[324];
- __shared__ float kernel_shared[576];
+extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[4];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[(((int)threadIdx.x) * 9)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 9) + 1)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 2)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 3)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 5)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 4)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 4)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 5)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 3)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 6)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 2)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 7)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 1)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 8)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 26) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 6) % 36) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 86) {
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 22) % 36) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ pad_temp_shared[(((int)threadIdx.x) * 48)] = ((((3 <= ((((int)threadIdx.x) * 16) % 27)) && (((((int)threadIdx.x) * 48) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 16) / 27) * 49)) + ((((((int)threadIdx.x) * 16) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 1)] = (((3 <= ((((int)threadIdx.x) * 16) % 27)) && ((((((int)threadIdx.x) * 48) + 1) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 16) / 27) * 49)) + ((((((int)threadIdx.x) * 16) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2)] = ((((3 <= ((((int)threadIdx.x) * 16) % 27)) && ((((((int)threadIdx.x) * 48) + 2) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 16) / 27) * 49)) + ((((((int)threadIdx.x) * 16) % 27) / 3) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 3)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 4)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 5)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 6)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 7)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 8)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 9)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 9) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 10)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 10) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 11)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 11) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 12)] = (((((3 <= (((((int)threadIdx.x) * 16) + 4) % 27)) && ((((((int)threadIdx.x) * 48) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 13)] = (((((3 <= (((((int)threadIdx.x) * 16) + 4) % 27)) && ((((((int)threadIdx.x) * 48) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 14)] = (((((3 <= (((((int)threadIdx.x) * 16) + 4) % 27)) && ((((((int)threadIdx.x) * 48) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 15)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 16)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 17)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 18)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 18) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 19)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 19) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 20)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 20) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 21)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 22)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 23)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 24)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 25)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 26)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 26) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 27)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 27) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 28)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 28) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 29)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 29) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 30)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 30) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 31)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 31) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 32)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 32) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 33)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 33) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 34)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 34) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 35)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 35) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 36)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 37)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 37) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 38)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 38) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 39)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 39) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 40)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 40) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 41)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 41) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 42)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 42) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 14) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 43)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 14) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 44)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 44) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 14) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 45)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 45) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 15) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 46)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 46) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 15) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 47)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 47) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 15) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2352)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2353)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2354)] = (((((3 <= (((((int)threadIdx.x) * 16) + 1) % 27)) && ((((((int)threadIdx.x) * 48) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2355)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2356)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2357)] = (((((3 <= (((((int)threadIdx.x) * 16) + 2) % 27)) && ((((((int)threadIdx.x) * 48) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2358)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 9) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 786) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2359)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 10) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 786) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2360)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 11) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 786) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2361)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 787) / 27) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2362)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 787) / 27) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2363)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 48) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 787) / 27) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2364)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 788) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2365)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 788) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2366)] = (((((3 <= (((((int)threadIdx.x) * 16) + 5) % 27)) && ((((((int)threadIdx.x) * 48) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 788) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2367)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 18) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 789) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2368)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 19) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 789) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2369)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 48) + 20) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 789) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2370)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 790) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2371)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 790) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2372)] = (((((3 <= (((((int)threadIdx.x) * 16) + 7) % 27)) && ((((((int)threadIdx.x) * 48) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 790) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2373)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 791) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2374)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 791) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2375)] = (((((3 <= (((((int)threadIdx.x) * 16) + 8) % 27)) && ((((((int)threadIdx.x) * 48) + 26) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 791) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2376)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 27) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 792) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2377)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 28) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 792) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2378)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 48) + 29) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 792) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2379)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 30) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 793) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2380)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 31) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 793) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2381)] = (((((3 <= (((((int)threadIdx.x) * 16) + 10) % 27)) && ((((((int)threadIdx.x) * 48) + 32) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 793) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2382)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 33) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 794) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2383)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 34) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 794) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2384)] = (((((3 <= (((((int)threadIdx.x) * 16) + 11) % 27)) && ((((((int)threadIdx.x) * 48) + 35) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 794) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2385)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 795) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2386)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 37) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 795) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2387)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 48) + 38) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 795) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2388)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 39) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 796) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2389)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 40) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 796) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2390)] = (((((3 <= (((((int)threadIdx.x) * 16) + 13) % 27)) && ((((((int)threadIdx.x) * 48) + 41) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 796) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2391)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 42) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 797) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2392)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 797) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2393)] = (((((3 <= (((((int)threadIdx.x) * 16) + 14) % 27)) && ((((((int)threadIdx.x) * 48) + 44) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 797) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2394)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 45) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 798) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2395)] = (((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 46) % 81) < 72)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 798) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2396)] = ((((1 <= ((((((int)threadIdx.x) * 16) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 48) + 47) % 81) < 72)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 798) / 27) * 49)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2397)] = (((((3 <= (((((int)threadIdx.x) * 16) + 16) % 27)) && ((((((int)threadIdx.x) * 48) + 48) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 3) % 9))) && ((((((int)threadIdx.x) * 3) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 799) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2398)] = (((((3 <= (((((int)threadIdx.x) * 16) + 16) % 27)) && ((((((int)threadIdx.x) * 48) + 49) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 4) % 9))) && ((((((int)threadIdx.x) * 3) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 799) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 5) {
+ pad_temp_shared[((((int)threadIdx.x) * 48) + 2399)] = (((((3 <= (((((int)threadIdx.x) * 16) + 16) % 27)) && ((((((int)threadIdx.x) * 48) + 50) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 3) + 5) % 9))) && ((((((int)threadIdx.x) * 3) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 16) + 799) / 27) * 49)) + (((((((int)threadIdx.x) * 16) + 16) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 3) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 49) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 98) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 147)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 196) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 245) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 245) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 343) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 55) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((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) + 441)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 441) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 153)];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 490) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 202) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 539)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 539) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 251) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 637)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 637) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 61) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 686) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 110) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 735)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 735) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 159)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((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) + 833)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 833) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 257) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 882) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 18)];
+ kernel_shared[(((int)threadIdx.x) + 931)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 931) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 67) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 116) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1029)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 1029) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 165)];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 1078) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 214) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 25) {
+ kernel_shared[(((int)threadIdx.x) + 1127)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 1127) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 263) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 288)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 324)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 289)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 325)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 290)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 326)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 297)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 333)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 298)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 334)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 299)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 335)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 360)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 108)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 396)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 73)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 361)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 109)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 397)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 74)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 362)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 110)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 398)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 81)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 369)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 117)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 405)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 82)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 370)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 118)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 406)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 83)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 371)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 119)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + 407)]));
- }
+ for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_outer_inner * 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 18) + 288)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 18) + 576)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 18) + 864)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 18) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 18) + 289)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 18) + 577)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 18) + 865)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 18) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 18) + 290)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 18) + 578)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 18) + 866)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 18) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 18) + 291)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 18) + 579)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 18) + 867)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 18) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 18) + 292)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 18) + 580)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 18) + 868)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 18) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 18) + 293)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 18) + 581)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 18) + 869)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 18) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 18) + 294)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 18) + 582)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 18) + 870)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 18) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 18) + 295)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 18) + 583)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 18) + 871)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 18) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 18) + 296)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 18) + 584)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 18) + 872)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 18) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 18) + 297)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 18) + 585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((rc_outer_inner * 18) + 873)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 18) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 18) + 298)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 18) + 586)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((rc_outer_inner * 18) + 874)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 18) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 18) + 299)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 18) + 587)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((rc_outer_inner * 18) + 875)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 18) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 18) + 300)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 18) + 588)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((rc_outer_inner * 18) + 876)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 18) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 18) + 301)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 18) + 589)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((rc_outer_inner * 18) + 877)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 18) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 18) + 302)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 18) + 590)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((rc_outer_inner * 18) + 878)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 18) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 18) + 303)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 18) + 591)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((rc_outer_inner * 18) + 879)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 18) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 18) + 304)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 18) + 592)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((rc_outer_inner * 18) + 880)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 18) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 18) + 305)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 18) + 593)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((rc_outer_inner * 18) + 881)]));
}
}
for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -868,7 +1325,7 @@ 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> ( 4 minutes 57.188 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 2.010 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 5ddce97fdc..c54a56f125 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)
- 8.2833 8.2820 8.2873 8.2807 0.0029
+ 8.1728 8.1735 8.1798 8.1650 0.0061
</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 3.571 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.662 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 7a6984d828..dd049cc812 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)
- 752.9399 751.8006 755.6409 751.3783 1.9177
+ 757.9659 758.9378 759.4680 755.4919 1.7627
</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 33.267 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.568 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 abf44aaa3c..30d1372802 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,32 +632,78 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 4) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 4) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 32) {
+ 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*8192) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*1024) + (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_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
- }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -695,7 +741,7 @@ 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: 1.464 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.775 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 4b2d1fe65f..046d49dd74 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>00:43.075</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:29.296</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,7 +349,7 @@
</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>00:43.039</p></td>
+<td><p>00:29.260</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>
@@ -357,7 +357,7 @@
<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>
-<td><p>00:00.005</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
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 ca7304c531..cb7e7d7c80 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -689,8 +689,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10223830
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9834524
+No: 2 GFLOPS: 1.91/1.91 result: MeasureResult(costs=(0.12134703050000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.425949811935425, timestamp=1666901230.1270561) [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3099700
+No: 3 GFLOPS: 0.00/1.91 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -812,8 +813,10 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4448839
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4418916
+No: 4 GFLOPS: 8.32/8.32 result: MeasureResult(costs=(0.02781081575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.8165857791900635, timestamp=1666901232.8728542) [('tile_f', [-1, 1, 4, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8910647
+No: 5 GFLOPS: 223.21/223.21 result: MeasureResult(costs=(0.001037167175257732,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4189164638519287, timestamp=1666901234.458369) [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7210757
+No: 6 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -935,8 +938,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8935055
-No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7796357
+No: 7 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1058,8 +1061,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3220060
-No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6707656
+No: 8 GFLOPS: 1.00/223.21 result: MeasureResult(costs=(0.23187986749999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.052842855453491, timestamp=1666901238.7628863) [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5243028
+No: 9 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1181,9 +1185,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,500929
-No: 6 GFLOPS: 31.87/31.87 result: MeasureResult(costs=(0.0072641439375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.912257194519043, timestamp=1666868320.6701288) [('tile_f', [-1, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7120334
-No: 7 GFLOPS: 0.00/31.87 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5094387
+No: 10 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1305,8 +1308,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10120885
-No: 8 GFLOPS: 0.00/31.87 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7763337
+No: 11 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1428,8 +1431,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4962390
-No: 9 GFLOPS: 0.00/31.87 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7140125
+No: 12 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1551,162 +1554,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10422980
-No: 10 GFLOPS: 70.99/70.99 result: MeasureResult(costs=(0.003260988285714286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6510119438171387, timestamp=1666868326.9700677) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1799056
-No: 11 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 143, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 71, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007fb94ffccfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
-Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6428638
-No: 12 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2309677
+No: 13 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1828,161 +1677,131 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5680057
-No: 13 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 512]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5714279
+No: 14 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ 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 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ 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):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 143, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 71, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007f3392bdbfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:1750
+ 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:1694
+ 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:1618
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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
+ 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 871, 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):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1778683
-No: 14 GFLOPS: 0.00/70.99 result: 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:1750
+ 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:1694
+ 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:1618
+ 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 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,926540
+No: 15 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2104,161 +1923,131 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3264168
-No: 15 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6254031
+No: 16 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ 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 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ 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):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 143, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 71, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007fb94ffccfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:1750
+ 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:1694
+ 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:1618
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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
+ 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 871, 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):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4052180
-No: 16 GFLOPS: 0.00/70.99 result: 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:1750
+ 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:1694
+ 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:1618
+ 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 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8224403
+No: 17 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2380,8 +2169,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4853360
-No: 17 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,827316
+No: 18 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2503,9 +2292,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9713552
-No: 18 GFLOPS: 7.84/70.99 result: MeasureResult(costs=(0.029541336,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1404051780700684, timestamp=1666868342.323972) [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5395338
-No: 19 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7775301
+No: 19 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2627,8 +2415,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1533209
-No: 20 GFLOPS: 0.00/70.99 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1152410
+No: 20 GFLOPS: 0.00/223.21 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2750,7 +2538,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,685169
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4209676
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2789,9 +2577,9 @@ 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, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1799056
+[('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7210757
Finish loading 20 records
-Time cost of this operator: 0.002250
+Time cost of this operator: 0.001410
</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 80f8c6704b..9b86467260 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -595,10 +595,10 @@ 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 312.8 98.72 (1, 2, 10, 10, 3) 2 1 [312.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.084 0.973 (1, 6, 10, 10) 1 1 [3.084]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.306 (1, 1, 10, 10, 3) 1 1 [0.97]
-Total_time - 316.854 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.725 (1, 2, 10, 10, 3) 2 1 [311.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.058 0.968 (1, 6, 10, 10) 1 1 [3.058]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.306 (1, 1, 10, 10, 3) 1 1 [0.968]
+Total_time - 315.826 - - - - -
</pre></div>
</div>
</div>
@@ -649,10 +649,10 @@ 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 106.4 97.585 (1, 6, 10, 10, 1) 2 1 [106.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.781 1.633 (1, 6, 10, 10) 1 1 [1.781]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.852 0.782 (1, 3, 10, 10, 1) 1 1 [0.852]
-Total_time - 109.033 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 136.7 98.107 (1, 6, 10, 10, 1) 2 1 [136.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.789 1.284 (1, 6, 10, 10) 1 1 [1.789]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.848 0.609 (1, 3, 10, 10, 1) 1 1 [0.848]
+Total_time - 139.338 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index eaf9689ac8..a1fa1caa6d 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -529,7 +529,7 @@ 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/tmpkjphwqie/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp3j4lhnrq/images/random'
</pre></div>
</div>
</div>
@@ -589,8 +589,8 @@ 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], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [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/tmpkjphwqie/images/target contains 8144 images
-/tmp/tmpkjphwqie/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], [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/tmp3j4lhnrq/images/target contains 8144 images
+/tmp/tmp3j4lhnrq/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -702,13 +702,13 @@ 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 - 48s - loss: 0.2697 - accuracy: 0.9175 - val_loss: 0.1813 - val_accuracy: 0.9339 - 48s/epoch - 145ms/step
+328/328 - 47s - loss: 0.2245 - accuracy: 0.9235 - val_loss: 0.1260 - val_accuracy: 0.9611 - 47s/epoch - 142ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0998 - accuracy: 0.9648 - val_loss: 0.1298 - val_accuracy: 0.9581 - 44s/epoch - 134ms/step
+328/328 - 43s - loss: 0.0913 - accuracy: 0.9668 - val_loss: 0.1235 - val_accuracy: 0.9562 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0739 - accuracy: 0.9723 - val_loss: 0.1250 - val_accuracy: 0.9569 - 44s/epoch - 134ms/step
+328/328 - 43s - loss: 0.0568 - accuracy: 0.9792 - val_loss: 0.1212 - val_accuracy: 0.9653 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7fa9b2063d50>
+<keras.callbacks.History object at 0x7f8a1c07cb10>
</pre></div>
</div>
</div>
@@ -970,7 +970,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 10.519 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 20.175 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 afbef9da74..37c36c162d 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>06:14.259</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:22.212</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:10.519</p></td>
+<td><p>04:20.175</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:51.518</p></td>
+<td><p>00:49.965</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.371</p></td>
+<td><p>00:08.262</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.849</p></td>
+<td><p>00:03.808</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 8ddd5ad75a..51f483b9f4 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>00:43.440</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.983</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>00:31.827</p></td>
+<td><p>00:32.167</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>00:10.084</p></td>
+<td><p>00:10.261</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>00:01.522</p></td>
+<td><p>00:01.547</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 4f9fcfc4d0..4611af38dd 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 0x7fa953e9aef0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f8a1033d290>
</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 da5c061f43..ff48855bf4 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>00:07.643</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.684</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</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>00:05.310</p></td>
+<td><p>00:05.206</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>00:01.017</p></td>
+<td><p>00:01.116</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>00:00.565</p></td>
+<td><p>00:00.595</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>00:00.546</p></td>
+<td><p>00:00.564</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>
@@ -369,11 +369,11 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.047</p></td>
+<td><p>00:00.046</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.029</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>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 1f521f1524..50acbc98f9 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -590,7 +590,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjdextzae/input0.cc'\nsource_filename = \"/tmp/tmpjdextzae/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/tmp7s1v3uwk/input0.cc'\nsource_filename = \"/tmp/tmp7s1v3uwk/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 6d75d3801e..77c9eed514 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 4ba07e0038..6435d186db 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/5c9066d81/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 a4b4f3d642..fd201c7321 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/5c9066d81/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 7a8a5e7834..257907b1e9 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/5c9066d81/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 98fb533971..ffa5185d0a 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/5c9066d81/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 f9801f4cbb..30650a0b9c 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/5c9066d81/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 1e309f31ad..36a76018a5 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/5c9066d81/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 b7ca2b0d6d..b0cdf253b7 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/5c9066d81/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 479f88c7aa..d6b0bd3170 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/5c9066d81/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 7f3933a608..f111fc1bea 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/5c9066d81/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 52ea0bdcfc..7e49a91253 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/5c9066d81/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 4b03b2e2f2..c8af9cd44f 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/5c9066d81/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 bbfd1235a7..2842a3d077 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/5c9066d81/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 17340642e1..19a2dd8af8 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/5c9066d81/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 b984a10780..17411e79cf 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/5c9066d81/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 a3676f45ae..150acc71f6 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/5c9066d81/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 b030f5310b..ab3d7296a5 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/5c9066d81/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 5d25ffb6a3..be30582b7c 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/5c9066d81/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 50db967b52..e13301990e 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/5c9066d81/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 5a8aeb1607..21d93b896d 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/5c9066d81/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 43a21522af..0ee19b7f7d 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/5c9066d81/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 8574aef512..b0ad5129e2 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/5c9066d81/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 74bc2f6136..a785475f1d 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/5c9066d81/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 f4f9342a18..2830ed0492 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/5c9066d81/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 d637dff0b0..ee363320ea 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/5c9066d81/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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/5c9066d81/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5acf3f90c/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 8d1c4b21f0..4570c0d193 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 f3c29bc2ee..4840aef353 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>00:27.158</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:26.283</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>00:27.152</p></td>
+<td><p>00:26.277</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 c08a3a74f2..e0e579311c 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 30.07s!
+resnet18_v1 inference graph built in 29.02s!
</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 3dded618f5..e0109eebed 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 19.88s!
+yolov3-tiny inference graph built in 19.23s!
</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 2cce841ec2..ac02ab1cb8 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>01:41.962</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:40.673</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>00:52.096</p></td>
+<td><p>00:51.685</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>00:49.866</p></td>
+<td><p>00:48.988</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 be28b42640..685d90ca25 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>00:03.161</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.163</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>00:02.712</p></td>
+<td><p>00:02.701</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>00:00.449</p></td>
+<td><p>00:00.462</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 9d2504b5d7..979cf4ef3f 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>00:00.771</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.848</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>00:00.404</p></td>
+<td><p>00:00.459</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>00:00.367</p></td>
+<td><p>00:00.389</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 57cf93a5d5..0f964bdd44 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -578,7 +578,7 @@ 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: 97.204 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 96.208 ms
</pre></div>
</div>
</div>
@@ -652,7 +652,7 @@ 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 18.688 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.112 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 a3cf048708..6a9bbc3937 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: 3.94/3.94 result: MeasureResult(costs=(0.0680505944,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.296668291091919, timestamp=1666866950.2135687) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
-No: 2 GFLOPS: 12.31/12.31 result: MeasureResult(costs=(0.021811631399999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5375258922576904, timestamp=1666866950.7758694) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
-No: 3 GFLOPS: 4.13/12.31 result: MeasureResult(costs=(0.0649240814,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1881957054138184, timestamp=1666866952.7357655) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
-No: 4 GFLOPS: 1.18/12.31 result: MeasureResult(costs=(0.2283630526,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7907021045684814, timestamp=1666866957.3120484) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
-No: 5 GFLOPS: 2.19/12.31 result: MeasureResult(costs=(0.1223811808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.114123821258545, timestamp=1666866959.5543363) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
-No: 6 GFLOPS: 1.89/12.31 result: MeasureResult(costs=(0.1419356216,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.421272039413452, timestamp=1666866962.7627308) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
-No: 7 GFLOPS: 4.24/12.31 result: MeasureResult(costs=(0.0632642322,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1744451522827148, timestamp=1666866963.9422517) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
-No: 8 GFLOPS: 3.43/12.31 result: MeasureResult(costs=(0.0782067068,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.448162317276001, timestamp=1666866965.4052196) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
-No: 9 GFLOPS: 0.51/12.31 result: MeasureResult(costs=(0.5260649714000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.524819374084473, timestamp=1666866974.273305) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
-No: 10 GFLOPS: 9.66/12.31 result: MeasureResult(costs=(0.027791939000000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.811206579208374, timestamp=1666866974.8884814) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+No: 1 GFLOPS: 1.63/1.63 result: MeasureResult(costs=(0.1645176604,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.775430679321289, timestamp=1666899866.2928798) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+No: 2 GFLOPS: 2.60/2.60 result: MeasureResult(costs=(0.1033720274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8303215503692627, timestamp=1666899868.1535747) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 3 GFLOPS: 12.23/12.23 result: MeasureResult(costs=(0.0219459878,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.49947690963745117, timestamp=1666899869.437013) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+No: 4 GFLOPS: 1.82/12.23 result: MeasureResult(costs=(0.147590579,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.47967791557312, timestamp=1666899872.7191708) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
+No: 5 GFLOPS: 3.06/12.23 result: MeasureResult(costs=(0.0877675978,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5474209785461426, timestamp=1666899874.4054992) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
+No: 6 GFLOPS: 3.17/12.23 result: MeasureResult(costs=(0.0847982484,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5069401264190674, timestamp=1666899875.923931) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
+No: 7 GFLOPS: 3.65/12.23 result: MeasureResult(costs=(0.0734906726,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3319902420043945, timestamp=1666899878.0177543) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+No: 8 GFLOPS: 4.11/12.23 result: MeasureResult(costs=(0.06527137820000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2480006217956543, timestamp=1666899879.2697284) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
+No: 9 GFLOPS: 3.90/12.23 result: MeasureResult(costs=(0.0687536636,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2471866607666016, timestamp=1666899880.6301255) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
+No: 10 GFLOPS: 2.16/12.23 result: MeasureResult(costs=(0.124356304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1012117862701416, timestamp=1666899882.783746) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
</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 0db146cf1a..fbffbb4d60 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': 517.6680545500018, 'median': 517.5069688999997, 'std': 2.239607076616047}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 516.2649050599839, 'median': 516.4274659000057, 'std': 2.3130655123629618}
</pre></div>
</div>
</div>
@@ -712,179 +712,178 @@ 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: 16.50/ 17.63 GFLOPS | Progress: (4/20) | 6.67 s
-[Task 1/25] Current/Best: 18.97/ 18.97 GFLOPS | Progress: (8/20) | 10.32 s
-[Task 1/25] Current/Best: 12.49/ 18.97 GFLOPS | Progress: (12/20) | 13.78 s
-[Task 1/25] Current/Best: 21.63/ 23.04 GFLOPS | Progress: (16/20) | 15.39 s
-[Task 1/25] Current/Best: 9.53/ 23.04 GFLOPS | Progress: (20/20) | 17.97 s Done.
+[Task 1/25] Current/Best: 12.64/ 13.44 GFLOPS | Progress: (4/20) | 9.21 s
+[Task 1/25] Current/Best: 1.92/ 16.60 GFLOPS | Progress: (8/20) | 13.33 s
+[Task 1/25] Current/Best: 7.15/ 17.69 GFLOPS | Progress: (12/20) | 17.09 s
+[Task 1/25] Current/Best: 17.59/ 17.69 GFLOPS | Progress: (16/20) | 19.01 s
+[Task 1/25] Current/Best: 21.90/ 23.12 GFLOPS | Progress: (20/20) | 20.96 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 13.19/ 14.78 GFLOPS | Progress: (4/20) | 3.20 s
-[Task 2/25] Current/Best: 12.90/ 14.78 GFLOPS | Progress: (8/20) | 5.03 s
-[Task 2/25] Current/Best: 9.52/ 22.05 GFLOPS | Progress: (12/20) | 6.66 s
-[Task 2/25] Current/Best: 12.01/ 22.05 GFLOPS | Progress: (16/20) | 7.97 s
-[Task 2/25] Current/Best: 8.73/ 22.05 GFLOPS | Progress: (20/20) | 9.35 s Done.
+[Task 2/25] Current/Best: 12.73/ 17.28 GFLOPS | Progress: (4/20) | 2.69 s
+[Task 2/25] Current/Best: 16.40/ 18.96 GFLOPS | Progress: (8/20) | 3.99 s
+[Task 2/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (12/20) | 5.26 s
+[Task 2/25] Current/Best: 13.63/ 19.01 GFLOPS | Progress: (16/20) | 6.89 s
+[Task 2/25] Current/Best: 16.84/ 20.54 GFLOPS | Progress: (20/20) | 8.91 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 14.11/ 17.45 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 3/25] Current/Best: 7.98/ 22.18 GFLOPS | Progress: (8/20) | 5.64 s
-[Task 3/25] Current/Best: 23.15/ 23.15 GFLOPS | Progress: (12/20) | 7.44 s
-[Task 3/25] Current/Best: 19.11/ 23.15 GFLOPS | Progress: (16/20) | 9.03 s
-[Task 3/25] Current/Best: 17.34/ 23.15 GFLOPS | Progress: (20/20) | 11.09 s Done.
+[Task 3/25] Current/Best: 13.40/ 22.65 GFLOPS | Progress: (4/20) | 3.44 s
+[Task 3/25] Current/Best: 6.37/ 22.65 GFLOPS | Progress: (8/20) | 6.20 s
+[Task 3/25] Current/Best: 13.70/ 22.65 GFLOPS | Progress: (12/20) | 8.08 s
+[Task 3/25] Current/Best: 20.72/ 22.65 GFLOPS | Progress: (16/20) | 10.09 s
+[Task 3/25] Current/Best: 10.24/ 22.65 GFLOPS | Progress: (20/20) | 12.44 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 6.38/ 9.97 GFLOPS | Progress: (4/20) | 7.54 s
-[Task 4/25] Current/Best: 4.58/ 17.01 GFLOPS | Progress: (8/20) | 9.25 s
-[Task 4/25] Current/Best: 5.56/ 17.01 GFLOPS | Progress: (12/20) | 11.16 s
-[Task 4/25] Current/Best: 13.05/ 19.90 GFLOPS | Progress: (16/20) | 13.11 s
-[Task 4/25] Current/Best: 19.46/ 19.90 GFLOPS | Progress: (20/20) | 18.92 s Done.
+[Task 4/25] Current/Best: 9.25/ 16.27 GFLOPS | Progress: (4/20) | 4.63 s
+[Task 4/25] Current/Best: 11.64/ 16.27 GFLOPS | Progress: (8/20) | 9.53 s
+[Task 4/25] Current/Best: 12.96/ 16.27 GFLOPS | Progress: (12/20) | 11.21 s
+[Task 4/25] Current/Best: 3.33/ 16.27 GFLOPS | Progress: (16/20) | 13.18 s
+[Task 4/25] Current/Best: 10.10/ 16.27 GFLOPS | Progress: (20/20) | 19.03 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 17.13/ 22.27 GFLOPS | Progress: (4/20) | 2.77 s
-[Task 5/25] Current/Best: 2.83/ 22.27 GFLOPS | Progress: (8/20) | 5.03 s
-[Task 5/25] Current/Best: 12.70/ 22.27 GFLOPS | Progress: (12/20) | 6.81 s
-[Task 5/25] Current/Best: 16.73/ 22.27 GFLOPS | Progress: (16/20) | 8.46 s
-[Task 5/25] Current/Best: 12.88/ 22.27 GFLOPS | Progress: (20/20) | 10.55 s Done.
+[Task 5/25] Current/Best: 11.11/ 22.20 GFLOPS | Progress: (4/20) | 2.92 s
+[Task 5/25] Current/Best: 14.70/ 22.20 GFLOPS | Progress: (8/20) | 4.51 s
+[Task 5/25] Current/Best: 15.30/ 22.20 GFLOPS | Progress: (12/20) | 6.23 s
+[Task 5/25] Current/Best: 15.85/ 22.20 GFLOPS | Progress: (16/20) | 8.53 s
+[Task 5/25] Current/Best: 6.54/ 22.20 GFLOPS | Progress: (20/20) | 10.71 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 4.47/ 15.99 GFLOPS | Progress: (4/20) | 3.44 s
-[Task 6/25] Current/Best: 17.66/ 17.66 GFLOPS | Progress: (8/20) | 5.37 s
-[Task 6/25] Current/Best: 13.05/ 17.66 GFLOPS | Progress: (12/20) | 8.25 s
-[Task 6/25] Current/Best: 3.94/ 17.66 GFLOPS | Progress: (16/20) | 11.17 s
-[Task 6/25] Current/Best: 7.95/ 17.66 GFLOPS | Progress: (20/20) | 14.59 s Done.
+[Task 6/25] Current/Best: 10.06/ 12.24 GFLOPS | Progress: (4/20) | 4.83 s
+[Task 6/25] Current/Best: 12.91/ 12.91 GFLOPS | Progress: (8/20) | 7.92 s
+[Task 6/25] Current/Best: 5.36/ 17.72 GFLOPS | Progress: (12/20) | 10.51 s
+[Task 6/25] Current/Best: 12.27/ 17.72 GFLOPS | Progress: (16/20) | 14.86 s
+[Task 6/25] Current/Best: 12.74/ 18.19 GFLOPS | Progress: (20/20) | 18.04 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 16.53/ 16.53 GFLOPS | Progress: (4/20) | 5.01 s
-[Task 7/25] Current/Best: 12.82/ 19.08 GFLOPS | Progress: (8/20) | 7.11 s
-[Task 7/25] Current/Best: 14.04/ 19.08 GFLOPS | Progress: (12/20) | 9.48 s
-[Task 7/25] Current/Best: 11.26/ 19.08 GFLOPS | Progress: (16/20) | 12.05 s
-[Task 7/25] Current/Best: 18.24/ 19.08 GFLOPS | Progress: (20/20) | 15.58 s Done.
+[Task 7/25] Current/Best: 19.11/ 19.52 GFLOPS | Progress: (4/20) | 3.01 s
+[Task 7/25] Current/Best: 11.38/ 19.52 GFLOPS | Progress: (8/20) | 6.07 s
+[Task 7/25] Current/Best: 9.56/ 19.52 GFLOPS | Progress: (12/20) | 9.64 s
+[Task 7/25] Current/Best: 8.70/ 19.52 GFLOPS | Progress: (16/20) | 11.77 s
+[Task 7/25] Current/Best: 14.21/ 19.52 GFLOPS | Progress: (20/20) | 14.61 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 2.69/ 14.55 GFLOPS | Progress: (4/20) | 4.72 s
-[Task 8/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (8/20) | 15.79 s
-[Task 8/25] Current/Best: 5.56/ 18.94 GFLOPS | Progress: (12/20) | 19.10 s
-[Task 8/25] Current/Best: 10.70/ 18.94 GFLOPS | Progress: (16/20) | 25.81 s
-[Task 8/25] Current/Best: 19.43/ 19.43 GFLOPS | Progress: (20/20) | 27.81 s
+[Task 8/25] Current/Best: 11.59/ 20.48 GFLOPS | Progress: (4/20) | 8.34 s
+[Task 8/25] Current/Best: 3.35/ 20.48 GFLOPS | Progress: (8/20) | 11.25 s
+[Task 8/25] Current/Best: 13.01/ 20.48 GFLOPS | Progress: (12/20) | 22.67 s
+[Task 8/25] Current/Best: 13.39/ 20.48 GFLOPS | Progress: (16/20) | 26.95 s
+[Task 8/25] Current/Best: 14.96/ 20.48 GFLOPS | Progress: (20/20) | 29.73 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 5.76/ 23.19 GFLOPS | Progress: (4/20) | 3.46 s
-[Task 9/25] Current/Best: 12.02/ 23.19 GFLOPS | Progress: (8/20) | 6.56 s
-[Task 9/25] Current/Best: 14.41/ 23.19 GFLOPS | Progress: (12/20) | 9.10 s
-[Task 9/25] Current/Best: 7.96/ 23.19 GFLOPS | Progress: (16/20) | 13.69 s
-[Task 9/25] Current/Best: 16.68/ 23.19 GFLOPS | Progress: (20/20) | 14.97 s Done.
+[Task 9/25] Current/Best: 3.20/ 17.00 GFLOPS | Progress: (4/20) | 9.93 s
+[Task 9/25] Current/Best: 16.43/ 17.00 GFLOPS | Progress: (8/20) | 12.85 s
+[Task 9/25] Current/Best: 12.94/ 17.00 GFLOPS | Progress: (12/20) | 15.12 s
+[Task 9/25] Current/Best: 10.24/ 17.00 GFLOPS | Progress: (16/20) | 18.69 s
+[Task 9/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (20/20) | 20.11 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 12.06/ 19.43 GFLOPS | Progress: (4/20) | 3.09 s
-[Task 10/25] Current/Best: 12.08/ 19.43 GFLOPS | Progress: (8/20) | 7.24 s
-[Task 10/25] Current/Best: 11.19/ 19.43 GFLOPS | Progress: (12/20) | 8.74 s
-[Task 10/25] Current/Best: 5.87/ 19.43 GFLOPS | Progress: (16/20) | 10.35 s
-[Task 10/25] Current/Best: 10.89/ 19.43 GFLOPS | Progress: (20/20) | 13.88 s Done.
+[Task 10/25] Current/Best: 13.22/ 14.53 GFLOPS | Progress: (4/20) | 3.50 s
+[Task 10/25] Current/Best: 5.62/ 19.73 GFLOPS | Progress: (8/20) | 4.93 s
+[Task 10/25] Current/Best: 17.32/ 20.96 GFLOPS | Progress: (12/20) | 6.38 s
+[Task 10/25] Current/Best: 5.71/ 20.96 GFLOPS | Progress: (16/20) | 8.25 s
+[Task 10/25] Current/Best: 14.31/ 20.96 GFLOPS | Progress: (20/20) | 9.65 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 8.38/ 16.22 GFLOPS | Progress: (4/20) | 3.85 s
-[Task 11/25] Current/Best: 6.70/ 23.90 GFLOPS | Progress: (8/20) | 6.60 s
-[Task 11/25] Current/Best: 14.85/ 23.90 GFLOPS | Progress: (12/20) | 8.87 s
-[Task 11/25] Current/Best: 16.08/ 23.90 GFLOPS | Progress: (16/20) | 10.94 s
-[Task 11/25] Current/Best: 10.18/ 23.90 GFLOPS | Progress: (20/20) | 13.18 s Done.
+[Task 11/25] Current/Best: 9.50/ 18.96 GFLOPS | Progress: (4/20) | 4.44 s
+[Task 11/25] Current/Best: 6.88/ 21.53 GFLOPS | Progress: (8/20) | 6.69 s
+[Task 11/25] Current/Best: 13.29/ 21.53 GFLOPS | Progress: (12/20) | 8.91 s
+[Task 11/25] Current/Best: 15.82/ 21.68 GFLOPS | Progress: (16/20) | 11.00 s
+[Task 11/25] Current/Best: 15.74/ 21.68 GFLOPS | Progress: (20/20) | 13.15 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 10.72/ 15.37 GFLOPS | Progress: (4/20) | 5.67 s
-[Task 12/25] Current/Best: 16.62/ 16.62 GFLOPS | Progress: (8/20) | 8.80 s
-[Task 12/25] Current/Best: 12.84/ 16.62 GFLOPS | Progress: (12/20) | 10.97 s
-[Task 12/25] Current/Best: 15.38/ 17.02 GFLOPS | Progress: (16/20) | 16.93 s
-[Task 12/25] Current/Best: 22.49/ 22.49 GFLOPS | Progress: (20/20) | 19.39 s Done.
+[Task 12/25] Current/Best: 11.30/ 14.30 GFLOPS | Progress: (4/20) | 4.54 s
+[Task 12/25] Current/Best: 13.17/ 14.30 GFLOPS | Progress: (8/20) | 7.18 s
+[Task 12/25] Current/Best: 14.18/ 14.48 GFLOPS | Progress: (12/20) | 9.67 s
+[Task 12/25] Current/Best: 14.25/ 14.48 GFLOPS | Progress: (16/20) | 16.07 s
+[Task 12/25] Current/Best: 9.49/ 14.48 GFLOPS | Progress: (20/20) | 18.37 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.28/ 16.95 GFLOPS | Progress: (4/20) | 5.04 s
-[Task 13/25] Current/Best: 17.85/ 17.85 GFLOPS | Progress: (8/20) | 8.89 s
-[Task 13/25] Current/Best: 14.13/ 18.98 GFLOPS | Progress: (12/20) | 10.65 s
-[Task 13/25] Current/Best: 15.22/ 18.98 GFLOPS | Progress: (16/20) | 13.01 s
-[Task 13/25] Current/Best: 6.52/ 19.37 GFLOPS | Progress: (20/20) | 15.67 s Done.
+[Task 13/25] Current/Best: 5.21/ 16.55 GFLOPS | Progress: (4/20) | 4.67 s
+[Task 13/25] Current/Best: 21.70/ 21.70 GFLOPS | Progress: (8/20) | 6.48 s
+[Task 13/25] Current/Best: 6.11/ 21.70 GFLOPS | Progress: (12/20) | 9.49 s
+[Task 13/25] Current/Best: 16.10/ 21.70 GFLOPS | Progress: (16/20) | 12.63 s
+[Task 13/25] Current/Best: 8.85/ 21.70 GFLOPS | Progress: (20/20) | 15.37 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 18.40/ 18.40 GFLOPS | Progress: (4/20) | 3.44 s
-[Task 14/25] Current/Best: 13.43/ 18.78 GFLOPS | Progress: (8/20) | 5.51 s
-[Task 14/25] Current/Best: 10.07/ 18.78 GFLOPS | Progress: (12/20) | 8.79 s
-[Task 14/25] Current/Best: 11.98/ 18.78 GFLOPS | Progress: (16/20) | 17.60 s
-[Task 14/25] Current/Best: 12.99/ 18.78 GFLOPS | Progress: (20/20) | 20.62 s
+[Task 14/25] Current/Best: 14.47/ 22.56 GFLOPS | Progress: (4/20) | 3.89 s
+[Task 14/25] Current/Best: 9.09/ 22.56 GFLOPS | Progress: (8/20) | 9.26 s
+[Task 14/25] Current/Best: 12.34/ 22.56 GFLOPS | Progress: (12/20) | 11.60 s
+[Task 14/25] Current/Best: 12.96/ 22.56 GFLOPS | Progress: (16/20) | 14.73 s
+[Task 14/25] Current/Best: 4.10/ 22.56 GFLOPS | Progress: (20/20) | 18.15 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-[Task 15/25] Current/Best: 15.58/ 20.74 GFLOPS | Progress: (4/20) | 7.25 s
-[Task 15/25] Current/Best: 3.18/ 20.74 GFLOPS | Progress: (8/20) | 9.52 s
-[Task 15/25] Current/Best: 16.97/ 20.74 GFLOPS | Progress: (12/20) | 11.20 s
-[Task 15/25] Current/Best: 14.72/ 20.77 GFLOPS | Progress: (16/20) | 12.82 s
-[Task 15/25] Current/Best: 18.64/ 20.77 GFLOPS | Progress: (20/20) | 14.76 s
+[Task 15/25] Current/Best: 14.66/ 22.12 GFLOPS | Progress: (4/20) | 6.32 s
+[Task 15/25] Current/Best: 13.11/ 22.12 GFLOPS | Progress: (8/20) | 8.10 s
+[Task 15/25] Current/Best: 15.53/ 22.12 GFLOPS | Progress: (12/20) | 9.56 s
+[Task 15/25] Current/Best: 10.55/ 22.12 GFLOPS | Progress: (16/20) | 13.34 s
+[Task 15/25] Current/Best: 19.95/ 22.12 GFLOPS | Progress: (20/20) | 17.51 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 8.07/ 11.80 GFLOPS | Progress: (4/20) | 4.03 s
-[Task 16/25] Current/Best: 14.70/ 14.70 GFLOPS | Progress: (8/20) | 6.23 s
-[Task 16/25] Current/Best: 9.84/ 14.70 GFLOPS | Progress: (12/20) | 9.06 s
-[Task 16/25] Current/Best: 6.09/ 17.65 GFLOPS | Progress: (16/20) | 10.97 s
-[Task 16/25] Current/Best: 12.93/ 17.65 GFLOPS | Progress: (20/20) | 12.47 s Done.
+[Task 16/25] Current/Best: 16.03/ 16.13 GFLOPS | Progress: (4/20) | 4.11 s
+[Task 16/25] Current/Best: 9.33/ 16.13 GFLOPS | Progress: (8/20) | 7.18 s
+[Task 16/25] Current/Best: 17.03/ 17.42 GFLOPS | Progress: (12/20) | 10.19 s
+[Task 16/25] Current/Best: 18.74/ 18.74 GFLOPS | Progress: (16/20) | 12.15 s
+[Task 16/25] Current/Best: 6.26/ 19.04 GFLOPS | Progress: (20/20) | 13.39 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 9.56/ 22.54 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 17/25] Current/Best: 20.05/ 22.54 GFLOPS | Progress: (8/20) | 6.16 s
-[Task 17/25] Current/Best: 12.71/ 22.54 GFLOPS | Progress: (12/20) | 8.08 s
-[Task 17/25] Current/Best: 12.89/ 22.54 GFLOPS | Progress: (16/20) | 9.87 s
-[Task 17/25] Current/Best: 11.70/ 22.54 GFLOPS | Progress: (20/20) | 12.84 s Done.
+[Task 17/25] Current/Best: 9.35/ 17.50 GFLOPS | Progress: (4/20) | 3.56 s
+[Task 17/25] Current/Best: 13.21/ 17.50 GFLOPS | Progress: (8/20) | 7.51 s
+[Task 17/25] Current/Best: 14.45/ 17.64 GFLOPS | Progress: (12/20) | 9.58 s
+[Task 17/25] Current/Best: 23.94/ 23.94 GFLOPS | Progress: (16/20) | 12.01 s
+[Task 17/25] Current/Best: 11.73/ 23.94 GFLOPS | Progress: (20/20) | 14.72 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 12.24/ 16.89 GFLOPS | Progress: (4/20) | 4.64 s
-[Task 18/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (8/20) | 6.84 s
-[Task 18/25] Current/Best: 12.19/ 20.54 GFLOPS | Progress: (12/20) | 12.78 s
-[Task 18/25] Current/Best: 10.75/ 20.54 GFLOPS | Progress: (16/20) | 15.83 s
-[Task 18/25] Current/Best: 18.90/ 20.54 GFLOPS | Progress: (20/20) | 19.21 s Done.
+[Task 18/25] Current/Best: 9.60/ 18.66 GFLOPS | Progress: (4/20) | 3.48 s
+[Task 18/25] Current/Best: 9.90/ 18.66 GFLOPS | Progress: (8/20) | 8.29 s
+[Task 18/25] Current/Best: 10.36/ 18.78 GFLOPS | Progress: (12/20) | 13.71 s
+[Task 18/25] Current/Best: 20.09/ 20.09 GFLOPS | Progress: (16/20) | 15.36 s
+[Task 18/25] Current/Best: 11.23/ 20.09 GFLOPS | Progress: (20/20) | 18.64 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 22.09/ 22.09 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 19/25] Current/Best: 9.05/ 22.09 GFLOPS | Progress: (8/20) | 6.71 s
-[Task 19/25] Current/Best: 17.67/ 22.09 GFLOPS | Progress: (12/20) | 9.98 s
-[Task 19/25] Current/Best: 3.09/ 22.09 GFLOPS | Progress: (16/20) | 13.58 s
-[Task 19/25] Current/Best: 17.89/ 22.09 GFLOPS | Progress: (20/20) | 15.72 s Done.
+[Task 19/25] Current/Best: 3.09/ 17.78 GFLOPS | Progress: (4/20) | 4.20 s
+[Task 19/25] Current/Best: 22.63/ 22.63 GFLOPS | Progress: (8/20) | 8.39 s
+[Task 19/25] Current/Best: 6.68/ 22.63 GFLOPS | Progress: (12/20) | 10.96 s
+[Task 19/25] Current/Best: 20.29/ 22.63 GFLOPS | Progress: (16/20) | 13.65 s
+[Task 19/25] Current/Best: 17.86/ 22.63 GFLOPS | Progress: (20/20) | 16.83 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 16.56/ 16.56 GFLOPS | Progress: (4/20) | 3.49 s
-[Task 20/25] Current/Best: 10.02/ 16.56 GFLOPS | Progress: (8/20) | 8.05 s
-[Task 20/25] Current/Best: 10.69/ 16.56 GFLOPS | Progress: (12/20) | 11.07 s
-[Task 20/25] Current/Best: 11.34/ 17.43 GFLOPS | Progress: (16/20) | 14.67 s
-[Task 20/25] Current/Best: 5.27/ 17.43 GFLOPS | Progress: (20/20) | 18.00 s
+[Task 20/25] Current/Best: 11.14/ 19.13 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 20/25] Current/Best: 12.93/ 19.13 GFLOPS | Progress: (8/20) | 5.15 s
+[Task 20/25] Current/Best: 8.49/ 19.13 GFLOPS | Progress: (12/20) | 11.32 s
+[Task 20/25] Current/Best: 2.25/ 20.28 GFLOPS | Progress: (16/20) | 14.81 s
+[Task 20/25] Current/Best: 9.60/ 20.28 GFLOPS | Progress: (20/20) | 17.22 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 7.83/ 18.05 GFLOPS | Progress: (4/20) | 3.76 s
-[Task 21/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (8/20) | 4.86 s
-[Task 21/25] Current/Best: 8.76/ 18.26 GFLOPS | Progress: (12/20) | 8.49 s Done.
- Done.
-
-[Task 21/25] Current/Best: 17.53/ 18.26 GFLOPS | Progress: (16/20) | 10.58 s
-[Task 21/25] Current/Best: 11.40/ 18.26 GFLOPS | Progress: (20/20) | 11.92 s
+[Task 21/25] Current/Best: 17.98/ 18.89 GFLOPS | Progress: (4/20) | 2.54 s
+[Task 21/25] Current/Best: 9.57/ 18.89 GFLOPS | Progress: (8/20) | 5.72 s
+[Task 21/25] Current/Best: 8.45/ 18.89 GFLOPS | Progress: (12/20) | 10.18 s
+[Task 21/25] Current/Best: 17.06/ 18.89 GFLOPS | Progress: (16/20) | 11.64 s
+[Task 21/25] Current/Best: 8.95/ 18.89 GFLOPS | Progress: (20/20) | 13.54 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 16.42/ 20.57 GFLOPS | Progress: (4/20) | 3.55 s
-[Task 22/25] Current/Best: 9.19/ 20.57 GFLOPS | Progress: (8/20) | 5.02 s
-[Task 22/25] Current/Best: 2.69/ 20.57 GFLOPS | Progress: (12/20) | 6.98 s
-[Task 22/25] Current/Best: 8.15/ 20.57 GFLOPS | Progress: (16/20) | 8.46 s
-[Task 22/25] Current/Best: 7.40/ 20.57 GFLOPS | Progress: (20/20) | 10.02 s Done.
+[Task 22/25] Current/Best: 14.11/ 21.67 GFLOPS | Progress: (4/20) | 3.88 s
+[Task 22/25] Current/Best: 14.54/ 21.67 GFLOPS | Progress: (8/20) | 6.92 s
+[Task 22/25] Current/Best: 5.50/ 21.67 GFLOPS | Progress: (12/20) | 8.42 s
+[Task 22/25] Current/Best: 6.47/ 21.67 GFLOPS | Progress: (16/20) | 13.83 s
+[Task 22/25] Current/Best: 6.81/ 21.67 GFLOPS | Progress: (20/20) | 16.31 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 6.54/ 14.75 GFLOPS | Progress: (4/20) | 5.27 s
-[Task 23/25] Current/Best: 10.00/ 21.95 GFLOPS | Progress: (8/20) | 7.27 s
-[Task 23/25] Current/Best: 9.65/ 21.95 GFLOPS | Progress: (12/20) | 10.15 s
-[Task 23/25] Current/Best: 12.89/ 21.95 GFLOPS | Progress: (16/20) | 12.49 s
-[Task 23/25] Current/Best: 16.28/ 22.65 GFLOPS | Progress: (20/20) | 14.44 s Done.
+[Task 23/25] Current/Best: 2.65/ 10.66 GFLOPS | Progress: (4/20) | 5.35 s
+[Task 23/25] Current/Best: 10.89/ 12.96 GFLOPS | Progress: (8/20) | 8.80 s
+[Task 23/25] Current/Best: 10.69/ 19.27 GFLOPS | Progress: (12/20) | 11.86 s
+[Task 23/25] Current/Best: 17.51/ 22.32 GFLOPS | Progress: (16/20) | 14.29 s
+[Task 23/25] Current/Best: 17.62/ 22.32 GFLOPS | Progress: (20/20) | 16.56 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.54/ 8.81 GFLOPS | Progress: (4/20) | 12.09 s
-[Task 24/25] Current/Best: 4.26/ 8.81 GFLOPS | Progress: (8/20) | 23.78 s
-[Task 24/25] Current/Best: 9.89/ 9.89 GFLOPS | Progress: (12/20) | 30.49 s
-[Task 24/25] Current/Best: 3.54/ 9.89 GFLOPS | Progress: (16/20) | 34.78 s
-[Task 24/25] Current/Best: 2.97/ 9.89 GFLOPS | Progress: (20/20) | 37.12 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+[Task 24/25] Current/Best: 3.96/ 8.78 GFLOPS | Progress: (4/20) | 12.30 s Done.
Done.
-[Task 25/25] Current/Best: 7.44/ 8.57 GFLOPS | Progress: (4/20) | 12.26 s
-[Task 25/25] Current/Best: 4.85/ 8.57 GFLOPS | Progress: (8/20) | 23.54 s
-[Task 25/25] Current/Best: 5.26/ 9.54 GFLOPS | Progress: (12/20) | 35.13 s
-[Task 25/25] Current/Best: 8.48/ 9.54 GFLOPS | Progress: (16/20) | 37.44 s
-[Task 25/25] Current/Best: 5.70/ 9.54 GFLOPS | Progress: (20/20) | 48.19 s
+[Task 24/25] Current/Best: 3.09/ 8.78 GFLOPS | Progress: (8/20) | 24.16 s
+[Task 24/25] Current/Best: 3.77/ 8.78 GFLOPS | Progress: (12/20) | 26.78 s
+[Task 24/25] Current/Best: 6.51/ 10.23 GFLOPS | Progress: (16/20) | 33.47 s
+[Task 24/25] Current/Best: 9.21/ 10.23 GFLOPS | Progress: (20/20) | 44.18 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 1.55/ 9.26 GFLOPS | Progress: (4/20) | 13.01 s
+[Task 25/25] Current/Best: 3.01/ 9.26 GFLOPS | Progress: (8/20) | 14.82 s
+[Task 25/25] Current/Best: 5.41/ 9.26 GFLOPS | Progress: (12/20) | 15.96 s
+[Task 25/25] Current/Best: 2.91/ 9.26 GFLOPS | Progress: (16/20) | 26.65 s
+[Task 25/25] Current/Best: 6.36/ 9.36 GFLOPS | Progress: (20/20) | 30.99 s Done.
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -945,8 +944,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
-class='n02123159 tiger cat' with probability=0.356379
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
+class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -983,8 +982,8 @@ 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': 421.82080812000095, 'median': 420.72292930000685, 'std': 2.864997551003513}
-unoptimized: {'mean': 517.6680545500018, 'median': 517.5069688999997, 'std': 2.239607076616047}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 412.1639453500211, 'median': 411.27183655003137, 'std': 2.848139501968217}
+unoptimized: {'mean': 516.2649050599839, 'median': 516.4274659000057, 'std': 2.3130655123629618}
</pre></div>
</div>
</div>
@@ -998,7 +997,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 48.633 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 57.187 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 db4006d8e7..07f1065f00 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>1.302e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.268e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index b599964414..f9c0ee2687 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -497,7 +497,7 @@ 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, 0xe5a19a0)), stage(b, placeholder(b, 0x5ed9210)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[it [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x23bbda40)), stage(b, placeholder(b, 0x213b4a70)), 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 052c32d489..26ac1640fa 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>14:17.415</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:25.291</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>10:48.633</p></td>
+<td><p>10:57.187</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>01:18.688</p></td>
+<td><p>01:26.112</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>01:02.066</p></td>
+<td><p>01:01.529</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:36.072</p></td>
+<td><p>00:35.486</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>00:29.813</p></td>
+<td><p>00:23.244</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>00:01.237</p></td>
+<td><p>00:00.796</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>00:00.745</p></td>
+<td><p>00:00.739</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>00:00.151</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>
@@ -388,7 +388,7 @@
<td><p>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<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>
@@ -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_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="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<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 5432aac920..bcf9d804a9 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: 0.000007
-naive: 0.000009
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -601,7 +601,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000009
</pre></div>
</div>
</div>
@@ -673,10 +673,10 @@ 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 6.555360000675137e-06 1.0
- naive 8.9559e-06 1.3661949914387055
-parallel 7.5355e-06 1.1495173414158673
- vector 2.4596199999999997e-05 3.752074637772271
+ numpy 7.828130001144019e-06 1.0
+ naive 6.9914000000000005e-06 0.8931124034703388
+parallel 9.033399999999999e-06 1.1539665282359695
+ vector 2.45923e-05 3.141529330300599
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -992,7 +992,7 @@ 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: 0.018763
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018316
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1033,7 +1033,7 @@ 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: 3.464069
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.418990
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1098,7 +1098,7 @@ 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: 0.310746
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.307668
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1157,7 +1157,7 @@ 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: 0.353294
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.348105
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1212,7 +1212,7 @@ 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: 0.118008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.125197
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1288,7 +1288,7 @@ 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: 0.107706
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109678
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1362,7 +1362,7 @@ 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: 0.110762
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111369
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1429,7 +1429,7 @@ 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: 0.146763
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.147371
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1491,13 +1491,13 @@ 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 3.4640688141 1.0
- blocking 0.3107459428 0.08970547626974175
- vectorization 0.3532940843 0.10198818304704763
-loop permutation 0.11800828 0.03406637868152736
- array packing 0.10770599039999999 0.031092335683863454
- block caching 0.1107623365 0.03197463516000538
- parallelization 0.1467633535 0.04236733199485548
+ none 3.4189896815 1.0
+ blocking 0.30766777419999997 0.08998792124608522
+ vectorization 0.348104966 0.10181515547811694
+loop permutation 0.12519716390000002 0.036618175415221714
+ array packing 0.10967809879999998 0.03207909617085517
+ block caching 0.1113691896 0.03257371328220547
+ parallelization 0.14737074339999998 0.043103594081437706
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1529,7 +1529,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.066 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.529 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>