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 2022/11/11 03:58:37 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@a15663654b4edcefa6431a1c3fb033069d17bc71)
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 9f6935a861 deploying docs (apache/tvm@a15663654b4edcefa6431a1c3fb033069d17bc71)
9f6935a861 is described below
commit 9f6935a8617976fe78570d8c75d3c690fd3883e7
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Nov 11 03:58:30 2022 +0000
deploying docs (apache/tvm@a15663654b4edcefa6431a1c3fb033069d17bc71)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 327199 -> 298414 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22934 -> 21680 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 | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 970 +++++++--------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 16 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 511 ++---------
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 14 +-
.../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 | 13 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 59 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 40 +-
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 | 15 +-
docs/how_to/compile_models/from_pytorch.html | 11 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 34 +-
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 | 39 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 970 +++++++--------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 16 +-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 511 ++---------
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 14 +-
.../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 | 9 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 269 +++---
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 30 +-
docs/tutorial/tensor_expr_get_started.html | 40 +-
127 files changed, 1561 insertions(+), 3053 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9acba7fd3b..b0585eecfd 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 fb0f49ab60..9b391c104b 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 8cd42a3e31..068eba65c7 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 12.775 seconds)
+ **Total running time of the script:** ( 1 minutes 14.452 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 2d0ddad9a3..35ff6fe2ee 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 936ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 958ms/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 5b827e4102..64dfe87f6c 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.zip29f59305-b4d0-4083-a467-7a6bf694e52a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipc1754c42-830c-451e-921c-9a3cab227639 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 31595a68e4..3fcfb075de 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]
15%|#5 | 6.33M/41.5M [00:00<00:00, 64.2MB/s]
30%|### | 12.5M/41.5M [00:00<00:00, 57.7MB/s]
43%|####3 | 18.0M/41.5M [00:00<00:00, 31.4MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 32.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 42.3MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 42.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 41.5MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 61.1MB/s]
29%|##9 | 12.2M/41.5M [00:00<00:00, 52.5MB/s]
42%|####1 | 17.2M/41.5M [00:00<00:00, 42.8MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 41.8MB/s]
64%|######3 | 26.4M/41.5M [00:00<00:00, 35.0MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.1MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 37.1MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 40.5MB/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 5aa1b248ea..350aa6b225 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]
18%|#7 | 7.99M/44.7M [00:00<00:00, 44.4MB/s]
36%|###5 | 16.0M/44.7M [00:00<00:00, 49.2MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 57.2MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 57.0MB/s]
86%|########5 | 38.3M/44.7M [00:00<00:00, 59.4MB/s]
99%|#########8| 44.1M/44.7M [00:00<00:00, 49.7MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 52.8MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.30M/44.7M [00:00<00:00, 42.9MB/s]
50%|##### | 22.5M/44.7M [00:00<00:00, 104MB/s]
93%|#########3| 41.6M/44.7M [00:00<00:00, 143MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 121MB/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 ecfc566d66..1d58cc4fdb 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 11.116 seconds)
+ **Total running time of the script:** ( 1 minutes 11.860 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 dc15adc83a..cb9eda6e74 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
=================
-**05:48.655** total execution time for **how_to_compile_models** files:
+**05:55.502** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:12.775 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:14.452 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.860 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.891 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.861 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.171 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:34.250 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.684 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.197 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.251 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.013 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.086 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.648 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.867 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.729 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.413 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.083 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.401 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.409 | 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 b631e2016b..6472033eed 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)
- 16.0904 16.0779 16.2258 15.9644 0.0912
+ 16.0995 16.0965 16.2038 15.9310 0.0747
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 63953a16df..33b4249657 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]
8%|7 | 13.5M/170M [00:00<00:01, 142MB/s]
16%|#5 | 27.1M/170M [00:00<00:01, 98.9MB/s]
24%|##3 | 40.0M/170M [00:00<00:01, 84.7MB/s]
33%|###2 | 56.0M/170M [00:00<00:01, 105MB/s]
40%|#### | 68.4M/170M [00:00<00:00, 112MB/s]
47%|####6 | 79.8M/170M [00:00<00:00, 108MB/s]
53%|#####3 | 90.5M/170M [00:00<00:00, 95.8MB/s]
61%|######1 | 104M/170M [00:01<00:00, 101MB/s]
67%|######7 | 114M/170M [00:01<00:00, 102MB/s]
73%|#######2 | 124M/170M [00:01<00:00, 97.4MB/s]
80%|######## | 136M/170M [00:01<00:00, 104MB/s]
87%|########6 | 148M/170M [00:01<00:00, 109MB/s]
93%|#########3| 158M/170M [00:01<00:00, 108MB/s]
99%|#########9| 169M/170M [00:01<00:00, 88.4MB/s]
100%|##########| 170M/170M [00:01<00:00, 99.9MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.68M/170M [00:00<00:02, 61.5MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 74.4MB/s]
14%|#3 | 23.2M/170M [00:00<00:02, 68.6MB/s]
18%|#7 | 29.9M/170M [00:00<00:02, 62.2MB/s]
21%|##1 | 35.9M/170M [00:00<00:02, 62.2MB/s]
28%|##8 | 48.0M/170M [00:00<00:01, 73.8MB/s]
35%|###5 | 59.6M/170M [00:00<00:01, 87.5MB/s]
44%|####3 | 74.1M/170M [00:01<00:01, 73.9MB/s]
48%|####8 | 81.7M/170M [00:01<00:01, 75.2MB/s]
55%|#####5 | 94.2M/170M [00:01<00:00, 88.8MB/s]
61%|###### | 103M/170M [00:01<00:00, 88.5MB/s]
66%|######6 | 112M/170M [00:01<00:00, 82.8MB/s]
71%|#######1 | 121M/170M [00:01<00:00, 86.2MB/s]
78%|#######8 | 133M/170M [00:01<00:00, 77.6MB/s]
87%|########6 | 148M/170M [00:01<00:00, 95.1MB/s]
93%|#########2| 157M/170M [00:02<00:00, 77.0MB/s]
100%|##########| 170M/170M [00:02<00:00, 81.6MB/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 14.467 seconds)
+ **Total running time of the script:** ( 3 minutes 19.195 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 b724485140..3d06ea8c79 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, 57.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 80.0MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
51%|##### | 6.90M/13.6M [00:00<00:00, 72.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 47.3MB/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)
- 90.2063 90.0435 94.8826 89.8450 0.5534
+ 90.5402 90.5235 91.2512 90.1183 0.2587
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.534 seconds)
+ **Total running time of the script:** ( 1 minutes 7.441 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 e2576ee534..28e027560e 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)
- 117.4192 117.1418 121.0319 115.9212 1.0907
+ 120.7630 120.7308 125.6918 119.9436 0.6827
@@ -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 21.628 seconds)
+ **Total running time of the script:** ( 2 minutes 29.523 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 89fa15f1a6..fe061dabfb 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 39.367 seconds)
+ **Total running time of the script:** ( 1 minutes 42.375 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 17d7d9ce80..a49f3a1f22 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%| | 881/132723 [00:00<00:14, 8804.01KB/s]
6%|5 | 7804/132723 [00:00<00:02, 44336.03KB/s]
12%|#1 | 15455/132723 [00:00<00:01, 59022.20KB/s]
17%|#7 | 23064/132723 [00:00<00:01, 65757.44KB/s]
22%|##2 | 29641/132723 [00:00<00:01, 61812.46KB/s]
27%|##7 | 35861/132723 [00:00<00:01, 56278.45KB/s]
33%|###2 | 43513/132723 [00:00<00:01, 62298.38KB/s]
39%|###8 | 51234/132723 [00:00<00:01, 66714.85KB/s]
44%|####4 | 58945/132723 [00:00<00:01, 69816.59KB/s]
50%|##### | 66625/132723 [00:01<00:00, 71904.08KB/s]
56%|#####5 | 74315/132723 [00:01<00:00, 73398.29KB/s]
62%|######1 | 81905/132723 [00:01<00:00, 68575.83KB/s]
67%|######7 | 89516/132723 [00:01<00:00, 70708.47KB/s]
73%|#######3 | 97235/132723 [00:01<00:00, 72576.09KB/s]
79%|#######8 | 104562/132723 [00:01<00:00, 68139.62KB/s]
84%|########3 | 1
11471/132723 [00:01<00:00, 64892.33KB/s]
89%|########8 | 118044/132723 [00:01<00:00, 62325.26KB/s]
95%|#########4| 125718/132723 [00:01<00:00, 66265.19KB/s]
100%|#########9| 132428/132723 [00:02<00:00, 64770.96KB/s]
100%|##########| 132723/132723 [00:02<00:00, 64741.57KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6384/132723 [00:00<00:01, 63834.43KB/s]
11%|#1 | 14877/132723 [00:00<00:01, 76237.41KB/s]
17%|#6 | 22501/132723 [00:00<00:01, 73641.01KB/s]
23%|##3 | 30988/132723 [00:00<00:01, 77977.35KB/s]
29%|##9 | 38802/132723 [00:00<00:01, 71845.13KB/s]
36%|###5 | 47245/132723 [00:00<00:01, 75852.64KB/s]
42%|####1 | 55713/132723 [00:00<00:00, 78611.30KB/s]
48%|####8 | 64161/132723 [00:00<00:00, 80422.36KB/s]
55%|#####4 | 72582/132723 [00:00<00:00, 81578.67KB/s]
61%|######1 | 81128/132723 [00:01<00:00, 82757.95KB/s]
68%|######7 | 89607/132723 [00:01<00:00, 83370.21KB/s]
74%|#######3 | 98208/132723 [00:01<00:00, 84165.99KB/s]
80%|######## | 106639/132723 [00:01<00:00, 69143.37KB/s]
87%|########6 | 115054/132723 [00:01<00:00, 73061.76KB/s]
93%|#########3| 123563/132723 [00:01<00:00, 76328.44KB/s]
99%|########
#9| 131917/132723 [00:01<00:00, 78341.77KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77343.86KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 56.256 seconds)
+ **Total running time of the script:** ( 3 minutes 3.896 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 28ad025c4c..0f22081e6b 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
=================
-**12:43.999** total execution time for **how_to_deploy_models** files:
+**13:10.505** 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``) | 03:14.467 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:19.195 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:56.256 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:03.896 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:21.628 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:29.523 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:39.367 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.375 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.534 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.441 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.547 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.611 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.389 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.026 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.804 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.431 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 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 aceb2b586d..165b6b5b04 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.zipd6fccdbd-a516-473d-9bbe-c59cb1199ecd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipfbd1211b-7e7d-4aa4-9bf7-36ba6ef28a7c 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 da12dc2cd7..d25cfd625c 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
=================
-**00:46.120** total execution time for **how_to_extend_tvm** files:
+**00:46.147** 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``) | 00:42.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:42.791 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.360 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.351 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.997 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 499eddb95c..a33aed96bd 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: 7138us [7138us] (46.33%; 46.33%)
- FoldScaleAxis: 8269us [6us] (53.67%; 53.67%)
- FoldConstant: 8263us [1700us] (53.63%; 99.92%)
- InferType: 6563us [6563us] (42.60%; 79.43%)
+ InferType: 7104us [7104us] (46.53%; 46.53%)
+ FoldScaleAxis: 8163us [6us] (53.47%; 53.47%)
+ FoldConstant: 8157us [1676us] (53.43%; 99.92%)
+ InferType: 6481us [6481us] (42.45%; 79.45%)
@@ -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: 6659us [6659us] (45.23%; 45.23%)
- FoldScaleAxis: 8065us [5us] (54.77%; 54.77%)
- FoldConstant: 8060us [1689us] (54.74%; 99.94%)
- InferType: 6371us [6371us] (43.27%; 79.04%)
+ InferType: 6487us [6487us] (44.94%; 44.94%)
+ FoldScaleAxis: 7947us [4us] (55.06%; 55.06%)
+ FoldConstant: 7942us [1639us] (55.03%; 99.94%)
+ InferType: 6303us [6303us] (43.67%; 79.36%)
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 de98725305..43d308b73a 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: 54.211456 ms
+ Convolution: 54.210494 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 8469cfcd3a..f0183c74ed 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: 13.069337 ms
+ conv2d with tensor core: 13.363360 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 b64e49a247..25237f8856 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: 0.017787
- Baseline: 3.315946
+ Numpy running time: 0.019615
+ Baseline: 3.374956
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.297152
+ Opt1: 0.296781
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.329254
+ Opt2: 0.339034
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.112337
+ Opt3: 0.118282
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.108558
+ Opt4: 0.109400
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110090
+ Opt5: 0.111530
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146061
+ Opt6: 0.147527
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 a7a2dfaa06..cfb62067d4 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.306** total execution time for **how_to_optimize_operators** files:
+**00:35.206** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.695 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.409 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.496 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.580 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.115 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.218 | 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 5369f5ea23..44aaeb6441 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:02.077** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:10.863** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:37.178 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:39.472 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.395 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.187 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.337 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.157 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.690 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:31.162 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.596 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.785 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.881 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.099 | 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 2cb946e373..aa2dadba6d 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
@@ -240,382 +240,184 @@ 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" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ 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, [9216]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 16) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
let cse_var_1: int32 = (rc.outer.outer*288)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 96), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*27)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 1)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 2)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 6)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 3)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 5)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 4)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 4)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 5)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 3)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 6)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 2)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 7)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 1)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 8)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 9)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 10)] = data[(((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21))]
- pad_temp.shared_1[((threadIdx.x_1*27) + 11)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 1)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 12)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 2)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 13)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 3)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 14)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 4)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 15)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 5)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 16)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 6)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 17)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 18)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 19)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 20)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 21)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 9)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 22)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 10)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 23)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 11)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 24)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 12)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 25)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 13)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 26)] = 0f32
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*6)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*2), 27)) && (floormod((threadIdx.x_1*6), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 27)*49)) + (floordiv(floormod((threadIdx.x_1*2), 27), 3)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*2), 27)) && (floormod(((threadIdx.x_1*6) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 27)*49)) + (floordiv(floormod((threadIdx.x_1*2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*2), 27)) && (floormod(((threadIdx.x_1*6) + 2), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 27)*49)) + (floordiv(floormod((threadIdx.x_1*2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 3), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 5), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 112), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1008), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3248), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3360), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3472), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3584), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3696), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3808), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4144), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4256), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4368), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4480), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4592), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4704), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4816)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4816), 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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4928), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5040)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5040), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5152)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5152), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5264)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5264), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5376), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5488)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5488), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5600)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5600), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5712)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5712), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5824), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5936)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5936), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6048)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6160)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6160), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6272)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6272), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6384)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6384), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6496)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6496), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6608)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6608), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6720)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6720), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6832)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6832), 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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6944)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6944), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7056)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7056), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7168), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7280), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7392), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7504)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7504), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7616)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7616), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7728)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7728), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7840), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7952), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8064)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8176)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8176), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8288)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8288), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8400)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8400), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8512)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8512), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8624)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8624), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8736)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8736), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8848)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8848), 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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8960)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 9072)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 9072), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 9184)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 9184), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1176)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 14), 27)) && (floormod(((threadIdx.x_1*6) + 42), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1177)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 14), 27)) && (floormod(((threadIdx.x_1*6) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1178)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 14), 27)) && (floormod(((threadIdx.x_1*6) + 44), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1179)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)) && (floormod(((threadIdx.x_1*6) + 45), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 27)*49)) + (floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1180)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)) && (floormod(((threadIdx.x_1*6) + 46), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 27)*49)) + (floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1181)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)) && (floormod(((threadIdx.x_1*6) + 47), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 27)*49)) + (floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
}
- for (rc.outer.inner: int32, 0, 4) {
- for (xx.outer.inner: int32, 0, 7) {
- let cse_var_2: int32 = (xx.outer.inner + 7)
- {
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72))]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[(((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4608)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 1)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4609)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 2)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4610)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 3)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4611)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4612)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 5)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4613)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 6)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4614)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 7)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4615)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 8)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4616)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 9)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4617)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 10)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4618)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 11)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4619)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 12)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4620)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 13)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4621)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 14)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4622)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 15)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4623)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 16)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4624)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 17)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4625)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 18)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4626)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 19)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4627)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 20)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4628)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 21)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4629)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 22)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4630)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 23)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4631)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 24)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4632)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 25)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4633)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 26)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4634)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 27)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4635)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 28)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4636)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 29)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4637)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 30)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4638)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 31)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4639)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 32)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4640)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 33)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4641)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 34)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4642)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 35)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4643)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 36)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4644)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 37)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4645)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 38)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4646)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 39)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4647)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 40)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4648)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 41)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4649)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 42)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4650)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 43)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4651)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 44)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4652)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 45)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4653)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 46)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4654)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 47)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4655)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 48)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4656)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 49)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4657)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 50)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4658)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 51)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4659)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 52)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4660)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 53)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4661)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 54)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4662)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 55)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4663)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 56)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4664)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 57)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4665)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 58)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4666)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 59)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4667)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 60)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4668)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 61)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4669)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 62)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4670)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 63)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4671)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 64)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4672)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 65)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4673)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 66)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4674)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 67)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4675)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 68)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4676)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 69)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4677)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 586)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 70)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 586)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4678)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 587)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 71)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 587)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4679)]))
- }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2352)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 3), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2353)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2354)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 5), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2355)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 2), 27)) && (floormod(((threadIdx.x_1*6) + 6), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
}
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2356)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 2), 27)) && (floormod(((threadIdx.x_1*6) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2357)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 2), 27)) && (floormod(((threadIdx.x_1*6) + 8), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*73728) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*73728) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1372), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 220), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1764), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2156), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2548), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 244), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2744), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2940), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3332), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3528), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3724), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 268), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4116), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4312), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 100), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4508), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 16) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2304)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 288)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2592)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2305)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 289)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2593)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2306)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 290)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2594)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2307)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 291)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2595)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2308)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 292)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2596)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2309)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 293)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2597)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2310)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 294)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2598)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2311)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 295)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2599)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2312)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 296)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2600)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2313)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 297)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2601)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2314)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 298)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2602)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2315)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 299)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2603)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2316)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 300)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2604)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2317)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 301)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2605)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2318)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 302)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2606)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2319)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 303)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2607)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2320)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 304)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2608)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2321)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 305)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2609)]))
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner) + 784)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
}
}
}
@@ -670,7 +472,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.270 ms
+ Execution time of this operator: 0.255 ms
@@ -718,20 +520,20 @@ 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=1)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
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_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
@@ -740,14 +542,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -767,12 +569,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
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=27)
+ 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=6)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -792,293 +594,151 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
+ extern "C" __global__ void __launch_bounds__(196) 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[9216];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 96) {
- pad_temp_shared[(((int)threadIdx.x) * 27)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 1)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 2)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 3)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 5)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 4)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 4)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 5)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 3)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 6)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 2)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 7)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 1)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 8)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 9)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 10)] = data[(((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21))];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 11)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 1)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 12)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 2)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 13)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 3)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 14)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 4)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 15)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 5)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 16)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 6)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 17)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 18)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 19)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 20)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 21)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 9)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 22)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 10)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 23)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 11)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 24)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 12)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 25)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 13)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 26)] = 0.000000e+00f;
+ pad_temp_shared[(((int)threadIdx.x) * 6)] = (((((3 <= ((((int)threadIdx.x) * 2) % 27)) && (((((int)threadIdx.x) * 6) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 27) * 49)) + ((((((int)threadIdx.x) * 2) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1)] = (((((3 <= ((((int)threadIdx.x) * 2) % 27)) && ((((((int)threadIdx.x) * 6) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 27) * 49)) + ((((((int)threadIdx.x) * 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2)] = (((((3 <= ((((int)threadIdx.x) * 2) % 27)) && ((((((int)threadIdx.x) * 6) + 2) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 27) * 49)) + ((((((int)threadIdx.x) * 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 3)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 3) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 4)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 5)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 5) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1176)] = (((((3 <= (((((int)threadIdx.x) * 2) + 14) % 27)) && ((((((int)threadIdx.x) * 6) + 42) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 392) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1177)] = (((((3 <= (((((int)threadIdx.x) * 2) + 14) % 27)) && ((((((int)threadIdx.x) * 6) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 392) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1178)] = (((((3 <= (((((int)threadIdx.x) * 2) + 14) % 27)) && ((((((int)threadIdx.x) * 6) + 44) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 392) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1179)] = (((((1 <= ((((((int)threadIdx.x) * 2) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 6) + 45) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 393) / 27) * 49)) + (((((((int)threadIdx.x) * 2) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1180)] = (((((1 <= ((((((int)threadIdx.x) * 2) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 6) + 46) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 393) / 27) * 49)) + (((((((int)threadIdx.x) * 2) / 3) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1181)] = (((((1 <= ((((((int)threadIdx.x) * 2) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 6) + 47) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 393) / 27) * 49)) + (((((((int)threadIdx.x) * 2) / 3) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2352)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 3) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2353)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2354)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 5) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3248) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3472) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3696) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4144) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4368) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4592) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4704) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 4816)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4816) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4928) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5040)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5040) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5152) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5264)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5264) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5376) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5488)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5488) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5600) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5712)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5712) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5824) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5936)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5936) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 6160)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6160) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6272) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6384)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6384) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 6496)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6496) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6608)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6608) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6720)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6720) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 6832)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6832) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6944)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6944) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7056)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7056) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7168) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7280) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7392) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7504)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7504) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7616)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7616) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7728)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7728) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7840) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7952) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 8176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8176) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8288)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8288) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8400)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8400) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 8512)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8512) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8624)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8624) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8736)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8736) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 8848)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8848) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8960) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 9072)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 9072) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 9184)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 9184) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 256) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2355)] = (((((3 <= (((((int)threadIdx.x) * 2) + 2) % 27)) && ((((((int)threadIdx.x) * 6) + 6) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2356)] = (((((3 <= (((((int)threadIdx.x) * 2) + 2) % 27)) && ((((((int)threadIdx.x) * 6) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2357)] = (((((3 <= (((((int)threadIdx.x) * 2) + 2) % 27)) && ((((((int)threadIdx.x) * 6) + 8) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 104) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 116) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 220) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 128) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 232) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 140) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 244) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 152) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 60)];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3332) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 164) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3528) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3724) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 268) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 176) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4116) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 84)];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4312) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 100) {
+ kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4508) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 188) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72))]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4608)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 1)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4609)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 2)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4610)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 3)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4611)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4612)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 5)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4613)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 6)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4614)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 7)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4615)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 8)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4616)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 9)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4617)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 10)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4618)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 11)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4619)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 12)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4620)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 13)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4621)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 14)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4622)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 15)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4623)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 16)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4624)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 17)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4625)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 18)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4626)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 19)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4627)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 20)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4628)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 21)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4629)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 22)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4630)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 23)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4631)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 24)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4632)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 25)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4633)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 26)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4634)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 27)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4635)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 28)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4636)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 29)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4637)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 30)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4638)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 31)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4639)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 32)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4640)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 33)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4641)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 34)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4642)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 35)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4643)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 36)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4644)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 37)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4645)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 38)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4646)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 39)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4647)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 40)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4648)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 41)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4649)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 42)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4650)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 43)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4651)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 44)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4652)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 45)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4653)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 46)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4654)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 47)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4655)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 48)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4656)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 49)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4657)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 50)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4658)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 51)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4659)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 52)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4660)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 53)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4661)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 54)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4662)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 55)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4663)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 56)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4664)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 57)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4665)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 58)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4666)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 59)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4667)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 60)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4668)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 61)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4669)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 62)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4670)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 63)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4671)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 64)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4672)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 65)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4673)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 66)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4674)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 67)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4675)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 68)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4676)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 69)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4677)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 586)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 70)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 586)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4678)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 587)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 71)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 587)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4679)]));
- }
+ 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) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2304)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 288)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2592)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2305)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 289)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2593)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2306)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 290)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2594)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2307)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 291)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2595)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2308)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 292)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2596)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2309)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 293)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2597)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2310)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 294)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2598)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2311)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 295)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2599)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2312)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 296)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2600)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2313)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 297)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2601)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2314)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 298)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2602)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2315)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 299)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2603)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2316)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 300)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2604)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2317)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 301)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2605)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2318)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 302)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2606)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2319)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 303)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2607)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2320)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 304)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2608)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2321)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 305)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2609)]));
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner) + 784)] = max((conv2d_nchw[(i3_inner + 7)] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
}
}
@@ -1140,7 +800,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 37.178 seconds)
+ **Total running time of the script:** ( 5 minutes 39.472 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 620703e337..f4c09bc74e 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)
- 8.1941 8.2051 8.2059 8.1713 0.0161
+ 8.1888 8.1820 8.2053 8.1790 0.0118
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.337 seconds)
+ **Total running time of the script:** ( 1 minutes 4.157 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 1da46eb369..442ed9ba80 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)
- 757.9147 756.8484 762.4136 754.4822 3.3246
+ 745.9471 746.3612 746.7702 744.7098 0.8907
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.395 seconds)
+ **Total running time of the script:** ( 1 minutes 33.187 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 11e66e39cf..0dcd27a1a6 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
@@ -386,13 +386,13 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
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, 16) {
+ for (i.outer.inner: int32, 0, 2) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (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
@@ -413,11 +413,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
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, 8) {
+ for (i.inner: int32, 0, 64) {
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*2048) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (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)
@@ -513,7 +513,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.861 ms
+ Execution time of this operator: 1.857 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 42d94b83c2..fb62169440 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
@@ -5,16 +5,16 @@
Computation times
=================
-**00:43.608** total execution time for **how_to_tune_with_autotvm** files:
+**00:50.049** 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``) | 00:43.572 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:50.014 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.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_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 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 7149c699f4..67a4871a85 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -265,9 +265,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 117.61/117.61 result: MeasureResult(costs=(0.0019684631967213117,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.218931436538696, timestamp=1668132414.1469023) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7292483
- No: 2 GFLOPS: 21.40/117.61 result: MeasureResult(costs=(0.0108182304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.342834711074829, timestamp=1668132414.8630574) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,485208
- No: 3 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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
@@ -389,163 +387,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9056115
- No: 4 GFLOPS: 2.58/117.61 result: MeasureResult(costs=(0.0898759765,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.753143072128296, timestamp=1668132417.2495856) [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,723215
- No: 5 GFLOPS: 9.71/117.61 result: MeasureResult(costs=(0.023840713500000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3782944679260254, timestamp=1668132419.5063689) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,855362
- No: 6 GFLOPS: 0.00/117.61 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 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, 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: 0x00007f7a550b6fa2
- 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, 32, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5269801
- No: 7 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8729037
+ No: 2 GFLOPS: 0.00/0.00 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
@@ -667,8 +510,9 @@ 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, 8, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 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,1532117
- No: 8 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1351202
+ No: 3 GFLOPS: 25.41/25.41 result: MeasureResult(costs=(0.009109318090909091,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7228238582611084, timestamp=1668134036.384868) [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6461748
+ No: 4 GFLOPS: 0.00/25.41 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
@@ -790,8 +634,8 @@ 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, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1001142
- No: 9 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1284068
+ No: 5 GFLOPS: 0.00/25.41 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
@@ -913,8 +757,8 @@ 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, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1471325
- No: 10 GFLOPS: 0.00/117.61 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, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6876097
+ No: 6 GFLOPS: 0.00/25.41 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
@@ -1036,8 +880,8 @@ 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, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3224715
- No: 11 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1353577
+ No: 7 GFLOPS: 0.00/25.41 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
@@ -1159,9 +1003,8 @@ 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, 128, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,256106
- No: 12 GFLOPS: 151.21/151.21 result: MeasureResult(costs=(0.001530953975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.975346326828003, timestamp=1668132427.996528) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8598500
- No: 13 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8320412
+ No: 8 GFLOPS: 0.00/25.41 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
@@ -1283,8 +1126,8 @@ 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, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8883032
- No: 14 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6346876
+ No: 9 GFLOPS: 0.00/25.41 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
@@ -1406,8 +1249,10 @@ 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, 32, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5164532
- No: 15 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1471435
+ No: 10 GFLOPS: 8.60/25.41 result: MeasureResult(costs=(0.026912216,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.046284914016724, timestamp=1668134042.8115733) [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4875818
+ No: 11 GFLOPS: 134.75/134.75 result: MeasureResult(costs=(0.0017180133050847457,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6454510688781738, timestamp=1668134043.4456222) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8335800
+ No: 12 GFLOPS: 0.00/134.75 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
@@ -1529,284 +1374,10 @@ 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, 2, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6029674
- No: 16 GFLOPS: 0.00/151.21 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 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h: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:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h: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
-
- 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:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h: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, 2, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10368315
- No: 17 GFLOPS: 0.00/151.21 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 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, 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: 0x00007f0ecb919fa2
- 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, 128, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5269987
- No: 18 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7218354
+ No: 13 GFLOPS: 70.22/134.75 result: MeasureResult(costs=(0.0032966100303030306,), error_no=MeasureErrorNo.NO_ERROR, all_cost=10.126962900161743, timestamp=1668134053.7817192) [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9959905
+ No: 14 GFLOPS: 10.27/134.75 result: MeasureResult(costs=(0.022534527999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7662863731384277, timestamp=1668134054.6339877) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8181689
+ No: 15 GFLOPS: 0.00/134.75 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
@@ -1928,8 +1499,8 @@ 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, 8, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7570183
- No: 19 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8533089
+ No: 16 GFLOPS: 0.00/134.75 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
@@ -2051,8 +1622,26 @@ 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, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2290340
- No: 20 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('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, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6771897
+ No: 17 GFLOPS: 0.00/134.75 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3009218
+ No: 18 GFLOPS: 0.00/134.75 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
@@ -2174,7 +1763,9 @@ 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, 2, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10021213
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8602196
+ No: 19 GFLOPS: 1.63/134.75 result: MeasureResult(costs=(0.14215892025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.336716651916504, timestamp=1668134067.0871265) [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6583704
+ No: 20 GFLOPS: 22.30/134.75 result: MeasureResult(costs=(0.010381638299999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6288275718688965, timestamp=1668134067.8301349) [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,233839
@@ -2229,9 +1820,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8598500
+ [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8335800
Finish loading 20 records
- Time cost of this operator: 0.001748
+ Time cost of this operator: 0.002147
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 781a87a528..8c3ed4d70e 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 311.1 98.727 (1, 2, 10, 10, 3) 2 1 [311.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.034 0.963 (1, 6, 10, 10) 1 1 [3.034]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.977 0.31 (1, 1, 10, 10, 3) 1 1 [0.977]
- Total_time - 315.11 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.5 98.713 (1, 2, 10, 10, 3) 2 1 [310.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.084 0.981 (1, 6, 10, 10) 1 1 [3.084]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.306 (1, 1, 10, 10, 3) 1 1 [0.963]
+ Total_time - 314.547 - - - - -
@@ -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 100.2 97.308 (1, 6, 10, 10, 1) 2 1 [100.2]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.812 1.759 (1, 6, 10, 10) 1 1 [1.812]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.933 (1, 1, 10, 10, 3) 1 1 [0.961]
- Total_time - 102.972 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.1 96.907 (1, 6, 10, 10, 1) 2 1 [100.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.052 1.987 (1, 6, 10, 10) 1 1 [2.052]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.143 1.106 (1, 1, 10, 10, 3) 1 1 [1.143]
+ Total_time - 103.295 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index d23e3d03bc..a09d13d45d 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
89%|########8 | 3.04M/3.42M [00:00<00:00, 31.7MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 33.5MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 88.0MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.674 seconds)
+ **Total running time of the script:** ( 1 minutes 2.012 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index f6cf83c82a..083ad9d6d0 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/tmppt6c9w_4/images/random'
+ '/tmp/tmp2w9e5ff8/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: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmppt6c9w_4/images/target contains 8144 images
- /tmp/tmppt6c9w_4/images/random contains 5000 images
+ /tmp/tmp2w9e5ff8/images/target contains 8144 images
+ /tmp/tmp2w9e5ff8/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2248 - accuracy: 0.9199 - val_loss: 0.1087 - val_accuracy: 0.9547 - 47s/epoch - 142ms/step
+ 328/328 - 46s - loss: 0.2100 - accuracy: 0.9274 - val_loss: 0.1252 - val_accuracy: 0.9581 - 46s/epoch - 140ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1000 - accuracy: 0.9631 - val_loss: 0.1361 - val_accuracy: 0.9551 - 43s/epoch - 131ms/step
+ 328/328 - 42s - loss: 0.1087 - accuracy: 0.9590 - val_loss: 0.1192 - val_accuracy: 0.9600 - 42s/epoch - 129ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0628 - accuracy: 0.9762 - val_loss: 0.0917 - val_accuracy: 0.9728 - 43s/epoch - 130ms/step
+ 328/328 - 42s - loss: 0.0666 - accuracy: 0.9762 - val_loss: 0.1455 - val_accuracy: 0.9509 - 42s/epoch - 129ms/step
- <keras.callbacks.History object at 0x7fa28c510750>
+ <keras.callbacks.History object at 0x7fe076b89dd0>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 41.388 seconds)
+ **Total running time of the script:** ( 4 minutes 33.607 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 f9af9c6615..1eb6adfc65 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
@@ -5,20 +5,20 @@
Computation times
=================
-**06:42.910** total execution time for **how_to_work_with_microtvm** files:
+**06:37.533** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:41.388 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:33.607 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:00.674 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.012 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:48.544 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.556 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.605 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.514 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.696 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.842 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.002 | 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 17be38252b..76e84bfff3 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
=================
-**00:43.233** total execution time for **how_to_work_with_relay** files:
+**00:44.789** 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``) | 00:31.398 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.863 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.239 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.515 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.590 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.404 | 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 f0578eadec..7c248a45a7 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 0x7fa28c8103b0>
+ <function my_cuda_math_rule at 0x7fe0d6b7e5f0>
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 bb160cbf98..25991389ba 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
=================
-**00:07.156** total execution time for **how_to_work_with_schedules** files:
+**00:05.084** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.772 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.512 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.067 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.154 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.561 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.613 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.544 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.593 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.115 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.032 | 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``) | 00:00.019 | 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 bcb0a823da..8417646469 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/tmp6nukmr7s/input0.cc'\nsource_filename = \"/tmp/tmp6nukmr7s/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/tmp6zlnhnuw/input0.cc'\nsource_filename = \"/tmp/tmp6zlnhnuw/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 9400eb9f05..7f8afaac6c 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
=================
-**00:25.396** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:25.595** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.390 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.589 | 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 6987c50615..32156aeefc 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 28.07s!
+ resnet18_v1 inference graph built in 28.14s!
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 d77505467c..fc64237e91 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 19.12s!
+ yolov3-tiny inference graph built in 18.94s!
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 295b9c3329..88d79f57a8 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
=================
-**01:39.292** total execution time for **topic_vta_tutorials_frontend** files:
+**01:38.981** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.315 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.069 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.977 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.912 | 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 ad733502c5..445bee736a 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
=================
-**00:03.107** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.199** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.665 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.716 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.442 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.483 | 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 f38c084472..6ae5f450a7 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
=================
-**00:00.794** total execution time for **topic_vta_tutorials** files:
+**00:00.849** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.430 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.441 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.364 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.408 | 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 a9b3ee801a..a423db7cbd 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,6 +203,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ *E
+ *E
+
@@ -326,7 +333,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.808 ms
+ Execution time of this operator: 95.889 ms
@@ -426,7 +433,7 @@ resume the status and do more 5 trials.
Resume search:
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-
+ *E
@@ -444,7 +451,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.868 seconds)
+ **Total running time of the script:** ( 1 minutes 43.051 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 ab710a8d03..74b1b4e8e3 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: 1.12/1.12 result: MeasureResult(costs=(0.2400360736,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.9573395252227783, timestamp=1668131036.1820025) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
- No: 2 GFLOPS: 9.07/9.07 result: MeasureResult(costs=(0.029596561400000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7329578399658203, timestamp=1668131036.863362) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
- No: 3 GFLOPS: 10.23/10.23 result: MeasureResult(costs=(0.0262403184,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.634730339050293, timestamp=1668131038.2000988) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
- No: 4 GFLOPS: 3.92/10.23 result: MeasureResult(costs=(0.068548571,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2965543270111084, timestamp=1668131040.2106373) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
- No: 5 GFLOPS: 1.84/10.23 result: MeasureResult(costs=(0.14577125159999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.464296817779541, timestamp=1668131042.8572454) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 6 GFLOPS: 1.43/10.23 result: MeasureResult(costs=(0.1875068702,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.125948905944824, timestamp=1668131046.020351) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
- No: 7 GFLOPS: 14.31/14.31 result: MeasureResult(costs=(0.0187537442,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5044946670532227, timestamp=1668131047.2417636) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
- No: 8 GFLOPS: 11.65/14.31 result: MeasureResult(costs=(0.023041929200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5674543380737305, timestamp=1668131047.813514) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
- No: 9 GFLOPS: 3.27/14.31 result: MeasureResult(costs=(0.08202040660000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4349756240844727, timestamp=1668131049.4001324) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
- No: 10 GFLOPS: 10.53/14.31 result: MeasureResult(costs=(0.025494058799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5698449611663818, timestamp=1668131049.972506) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
+ No: 1 GFLOPS: 0.89/0.89 result: MeasureResult(costs=(0.3007659048,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.955992698669434, timestamp=1668132616.9510393) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+ No: 2 GFLOPS: 10.80/10.80 result: MeasureResult(costs=(0.0248455454,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5782978534698486, timestamp=1668132617.5614326) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 3 GFLOPS: 12.39/12.39 result: MeasureResult(costs=(0.0216652868,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.48595094680786133, timestamp=1668132618.8351378) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
+ No: 4 GFLOPS: 13.14/13.14 result: MeasureResult(costs=(0.0204259016,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4742145538330078, timestamp=1668132620.0899937) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+ No: 5 GFLOPS: 1.72/13.14 result: MeasureResult(costs=(0.1560466606,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.606656789779663, timestamp=1668132622.8635302) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 6 GFLOPS: 0.95/13.14 result: MeasureResult(costs=(0.2838922176,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.699040412902832, timestamp=1668132628.3293188) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
+ No: 7 GFLOPS: 10.82/13.14 result: MeasureResult(costs=(0.024816031199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5873422622680664, timestamp=1668132628.8960543) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+ No: 8 GFLOPS: 1.22/13.14 result: MeasureResult(costs=(0.2194521924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.6838390827178955, timestamp=1668132632.6119697) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+ No: 9 GFLOPS: 10.90/13.14 result: MeasureResult(costs=(0.0246296524,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5192666053771973, timestamp=1668132633.2504795) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
+ No: 10 GFLOPS: 1.58/13.14 result: MeasureResult(costs=(0.1694415808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.830249309539795, timestamp=1668132636.127075) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index b1b27df5b8..f89069354a 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 513.8065643800019, 'median': 513.9278934999766, 'std': 1.6299110458413983}
+ {'mean': 514.875446879978, 'median': 515.1379385999917, 'std': 1.4243465931917811}
@@ -554,30 +554,29 @@ 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: 23.56/ 23.56 GFLOPS | Progress: (4/20) | 8.20 s
[Task 1/25] Current/Best: 17.80/ 23.56 GFLOPS | Progress: (8/20) | 12.71 s
[Task 1/25] Current/Best: 15.20/ 23.56 GFLOPS | Progress: (12/20) | 14.64 s
[Task 1/25] Current/Best: 17.53/ 23.56 GFLOPS | Progress: (16/20) | 16.59 s
[Task 1/25] Current/Best: 9.70/ 23.56 GFLOPS | Progress: (20/20) | 20.07 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 6.14/ 20.75 GFLOPS | Progress: (4/20) | 2.52 s
[Task 2/25] Current/Best: 19.08/ 20.75 GFLOPS | Progress: (8/20) | 3.87 s
[Task 2/25] Current/Best: 9.90/ 20.75 GFLOPS | Progress: (12/20) | 5.45 s
[Task 2/25] Current/Best: 6.00/ 20.75 GFLOPS | Progress: (16/20) | 6.87 s
[Task 2/25] Current/Best: 12.18/ 20.75 GFLOPS | Progress: (20/20) | 8.63 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 11.99/ 11.99 GFLOPS | Progress: (4/20) | 4.04 s
[Task 3/25] Current/Best: 15.74/ 21.45 GFLOPS | Progress: (8/20) | 5.68 s
[Task 3/25] Current/Best: 3.17/ 21.45 GFLOPS | Progress: (12/20) | 8.37 s
[Task 3/25] Current/Best: 9.86/ 21.45 GFLOPS | Progress: (16/20) | 10.80 s
[Task 3/25] Current/Best: 13.55/ 21.45 GFLOPS | Progress: (20/20) | 12.77 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.32/ 21.55 GFLOPS | Progress: (4/20) | 3.90 s
[Task 4/25] Current/Best: 8.01/ 22.97 GFLOPS | Progress: (8/20) | 5.98 s
[Task 4/25] Current/Best: 6.20/ 22.97 GFLOPS | Progress: (12/20) | 7.89 s
[Task 4/25] Current/Best: 2.28/ 22.97 GFLOPS | Progress: (16/20) | 9.61 s
[Task 4/25] Current/Best: 11.70/ 22.97 GFLOPS | Progress: (20/20) | 12.50 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 5.61/ 18.16 GFLOPS | Progress: (4/20) | 3.50 s
[Task 5/25] Current/Best: 6.17/ 18.16 GFLOPS | Progress: (8/20) | 5.70 s
[Task 5/25] Current/Best: 12.76/ 18.16 GFLOPS | Progress: (12/20) | 7.72 s
[Task 5/25] Current/Best: 16.19/ 18.16 GFLOPS | Progress: (16/20) | 9.54 s
[Task 5/25] Current/Best: 16.15/ 18.16 GFLOPS | Progress: (20/20) | 11.31 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 13.95/ 17.78 GFLOPS | Progress: (4/20) | 4.78 s
[Task 6/25] Current/Best: 10.09/ 17.78 GFLOPS | Progress: (8/20) | 6.98 s
[Task 6/25] Current/Best: 5.54/ 17.78 GFLOPS | Progress: (12/20) | 10.12 s
[Task 6/25] Current/Best: 14.06/ 17.78 GFLOPS | Progress: (16/20) | 13.13 s
[Task 6/25] Current/Best: 14.70/ 17.78 GFLOPS | Progress: (20/20) | 16.05 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 3.14/ 18.40 GFLOPS | Progress: (4/20) | 3.76 s
[Task 7/25] Current/Best: 15.23/ 19.39 GFLOPS | Progress: (8/20) | 6.18 s
[Task 7/25] Current/Best: 6.82/ 19.39 GFLOPS | Progress: (12/20) | 8.27 s
[Task 7/25] Current/Best: 18.40/ 19.39 GFLOPS | Progress: (16/20) | 10.36 s
[Task 7/25] Current/Best: 5.46/ 22.40 GFLOPS | Progress: (20/20) | 12.45 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.91/ 12.58 GFLOPS | Progress: (4/20) | 7.42 s
[Task 8/25] Current/Best: 12.75/ 12.75 GFLOPS | Progress: (8/20) | 11.96 s
[Task 8/25] Current/Best: 5.56/ 15.61 GFLOPS | Progress: (12/20) | 15.09 s
[Task 8/25] Current/Best: 3.50/ 15.78 GFLOPS | Progress: (16/20) | 17.79 s
[Task 8/25] Current/Best: 9.73/ 15.78 GFLOPS | Progress: (20/20) | 25.47 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 8.45/ 12.36 GFLOPS | Progress: (4/20) | 5.44 s
[Task 9/25] Current/Best: 8.90/ 12.36 GFLOPS | Progress: (8/20) | 7.65 s
[Task 9/25] Current/Best: 6.56/ 20.30 GFLOPS | Progress: (12/20) | 9.16 s
[Task 9/25] Current/Best: 17.04/ 21.09 GFLOPS | Progress: (16/20) | 11.58 s
[Task 9/25] Current/Best: 6.86/ 21.09 GFLOPS | Progress: (20/20) | 16.57 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.02/ 22.21 GFLOPS | Progress: (4/20) | 2.73 s
[Task 10/25] Current/Best: 5.43/ 22.21 GFLOPS | Progress: (8/20) | 4.28 s
[Task 10/25] Current/Best: 10.01/ 22.21 GFLOPS | Progress: (12/20) | 5.81 s
[Task 10/25] Current/Best: 13.95/ 22.21 GFLOPS | Progress: (16/20) | 7.36 s
[Task 10/25] Current/Best: 1.59/ 22.21 GFLOPS | Progress: (20/20) | 9.34 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 18.62/ 18.62 GFLOPS | Progress: (4/20) | 3.06 s
[Task 11/25] Current/Best: 14.35/ 22.59 GFLOPS | Progress: (8/20) | 4.93 s
[Task 11/25] Current/Best: 11.32/ 22.59 GFLOPS | Progress: (12/20) | 7.59 s
[Task 11/25] Current/Best: 21.23/ 22.59 GFLOPS | Progress: (16/20) | 9.50 s
[Task 11/25] Current/Best: 9.90/ 22.59 GFLOPS | Progress: (20/20) | 11.64 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 1.58/ 15.73 GFLOPS | Progress: (4/20) | 7.13 s
[Task 12/25] Current/Best: 13.49/ 21.09 GFLOPS | Progress: (8/20) | 10.57 s
[Task 12/25] Current/Best: 13.01/ 21.09 GFLOPS | Progress: (12/20) | 18.78 s
[Task 12/25] Current/Best: 9.75/ 21.09 GFLOPS | Progress: (16/20) | 22.68 s
[Task 12/25] Current/Best: 21.04/ 21.09 GFLOPS | Progress: (20/20) | 25.74 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 12.67/ 18.71 GFLOPS | Progress: (4/20) | 4.63 s
[Task 13/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (8/20) | 7.69 s
[Task 13/25] Current/Best: 17.06/ 21.36 GFLOPS | Progress: (12/20) | 11.16 s
[Task 13/25] Current/Best: 17.28/ 21.36 GFLOPS | Progress: (16/20) | 14.34 s
[Task 13/25] Current/Best: 18.82/ 21.36 GFLOPS | Progress: (20/20) | 16.41 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.12/ 21.18 GFLOPS | Progress: (4/20) | 3.39 s
[Task 14/25] Current/Best: 15.44/ 21.18 GFLOPS | Progress: (8/20) | 5.17 s
[Task 14/25] Current/Best: 17.47/ 21.18 GFLOPS | Progress: (12/20) | 9.33 s
[Task 14/25] Current/Best: 12.19/ 21.18 GFLOPS | Progress: (16/20) | 11.32 s
[Task 14/25] Current/Best: 18.83/ 21.18 GFLOPS | Progress: (20/20) | 14.87 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.93/ 13.93 GFLOPS | Progress: (4/20) | 5.06 s
[Task 15/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (8/20) | 8.73 s
[Task 15/25] Current/Best: 9.29/ 19.69 GFLOPS | Progress: (12/20) | 9.90 s Done.
-
[Task 15/25] Current/Best: 19.66/ 19.69 GFLOPS | Progress: (16/20) | 11.23 s
[Task 15/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (20/20) | 12.45 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 10.28/ 17.61 GFLOPS | Progress: (4/20) | 3.96 s
[Task 16/25] Current/Best: 5.87/ 20.29 GFLOPS | Progress: (8/20) | 5.29 s
[Task 16/25] Current/Best: 15.80/ 20.29 GFLOPS | Progress: (12/20) | 6.89 s
[Task 16/25] Current/Best: 13.77/ 20.29 GFLOPS | Progress: (16/20) | 8.66 s
[Task 16/25] Current/Best: 14.99/ 20.29 GFLOPS | Progress: (20/20) | 10.21 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 15.48/ 21.80 GFLOPS | Progress: (4/20) | 3.37 s
[Task 17/25] Current/Best: 12.25/ 21.80 GFLOPS | Progress: (8/20) | 5.24 s
[Task 17/25] Current/Best: 17.77/ 21.80 GFLOPS | Progress: (12/20) | 7.51 s
[Task 17/25] Current/Best: 7.65/ 21.80 GFLOPS | Progress: (16/20) | 10.21 s
[Task 17/25] Current/Best: 9.95/ 21.80 GFLOPS | Progress: (20/20) | 12.54 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 13.46/ 16.11 GFLOPS | Progress: (4/20) | 3.45 s
[Task 18/25] Current/Best: 6.52/ 18.10 GFLOPS | Progress: (8/20) | 5.36 s
[Task 18/25] Current/Best: 13.83/ 18.10 GFLOPS | Progress: (12/20) | 9.70 s
[Task 18/25] Current/Best: 3.04/ 20.16 GFLOPS | Progress: (16/20) | 12.38 s
[Task 18/25] Current/Best: 13.67/ 20.16 GFLOPS | Progress: (20/20) | 15.65 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.78/ 20.90 GFLOPS | Progress: (4/20) | 4.43 s
[Task 19/25] Current/Best: 17.06/ 20.90 GFLOPS | Progress: (8/20) | 9.08 s
[Task 19/25] Current/Best: 12.62/ 20.90 GFLOPS | Progress: (12/20) | 12.41 s
[Task 19/25] Current/Best: 16.05/ 20.90 GFLOPS | Progress: (16/20) | 15.80 s
[Task 19/25] Current/Best: 3.08/ 20.90 GFLOPS | Progress: (20/20) | 20.03 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 14.81/ 17.50 GFLOPS | Progress: (4/20) | 3.28 s
[Task 20/25] Current/Best: 9.32/ 17.50 GFLOPS | Progress: (8/20) | 5.42 s
[Task 20/25] Current/Best: 10.26/ 17.50 GFLOPS | Progress: (12/20) | 8.56 s
[Task 20/25] Current/Best: 15.18/ 17.50 GFLOPS | Progress: (16/20) | 10.55 s
[Task 20/25] Current/Best: 6.18/ 17.50 GFLOPS | Progress: (20/20) | 14.05 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 10.67/ 10.67 GFLOPS | Progress: (4/20) | 3.45 s Done.
-
[Task 21/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (8/20) | 5.53 s
[Task 21/25] Current/Best: 8.04/ 18.81 GFLOPS | Progress: (12/20) | 7.48 s
[Task 21/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (16/20) | 9.14 s
[Task 21/25] Current/Best: 17.75/ 19.24 GFLOPS | Progress: (20/20) | 11.52 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 7.96/ 14.11 GFLOPS | Progress: (4/20) | 5.49 s
[Task 22/25] Current/Best: 20.39/ 20.39 GFLOPS | Progress: (8/20) | 6.94 s
[Task 22/25] Current/Best: 7.65/ 20.39 GFLOPS | Progress: (12/20) | 9.17 s
[Task 22/25] Current/Best: 17.60/ 20.39 GFLOPS | Progress: (16/20) | 11.89 s
[Task 22/25] Current/Best: 16.22/ 20.39 GFLOPS | Progress: (20/20) | 16.59 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 8.01/ 19.48 GFLOPS | Progress: (4/20) | 4.25 s
[Task 23/25] Current/Best: 18.84/ 19.48 GFLOPS | Progress: (8/20) | 6.69 s
[Task 23/25] Current/Best: 19.88/ 19.88 GFLOPS | Progress: (12/20) | 8.71 s
[Task 23/25] Current/Best: 17.15/ 19.88 GFLOPS | Progress: (16/20) | 12.90 s
[Task 23/25] Current/Best: 19.48/ 19.88 GFLOPS | Progress: (20/20) | 15.59 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 9.55/ 9.55 GFLOPS | Progress: (4/20) | 12.24 s
[Task 24/25] Current/Best: 7.52/ 9.55 GFLOPS | Progress: (8/20) | 23.51 s
[Task 24/25] Current/Best: 3.47/ 9.55 GFLOPS | Progress: (12/20) | 25.65 s
[Task 24/25] Current/Best: 3.21/ 9.55 GFLOPS | Progress: (16/20) | 36.39 s
[Task 24/25] Current/Best: 3.61/ 9.55 GFLOPS | Progress: (20/20) | 39.63 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 7.58/ 7.58 GFLOPS | Progress: (4/20) | 12.25 s
[Task 25/25] Current/Best: 8.21/ 8.56 GFLOPS | Progress: (8/20) | 22.38 s
[Task 25/25] Current/Best: 3.46/ 8.56 GFLOPS | Progress: (12/20) | 23.55 s
[Task 25/25] Current/Best: 1.55/ 8.56 GFLOPS | Progress: (16/20) | 30.83 s
[Task 25/25] Current/Best: 7.54/ 8.56 GFLOPS | Progress: (20/20) | 41.56 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.16/ 16.54 GFLOPS | Progress: (4/20) | 6.71 s
[Task 1/25] Current/Best: 6.76/ 16.54 GFLOPS | Progress: (8/20) | 10.48 s
[Task 1/25] Current/Best: 9.72/ 23.02 GFLOPS | Progress: (12/20) | 14.04 s
[Task 1/25] Current/Best: 15.85/ 23.02 GFLOPS | Progress: (16/20) | 16.53 s
[Task 1/25] Current/Best: 18.93/ 23.02 GFLOPS | Progress: (20/20) | 18.74 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 9.62/ 17.29 GFLOPS | Progress: (4/20) | 2.78 s
[Task 2/25] Current/Best: 13.01/ 17.29 GFLOPS | Progress: (8/20) | 3.96 s
[Task 2/25] Current/Best: 10.80/ 18.27 GFLOPS | Progress: (12/20) | 5.01 s
[Task 2/25] Current/Best: 16.05/ 18.27 GFLOPS | Progress: (16/20) | 6.65 s
[Task 2/25] Current/Best: 14.35/ 18.27 GFLOPS | Progress: (20/20) | 7.95 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 5.79/ 14.43 GFLOPS | Progress: (4/20) | 3.87 s
[Task 3/25] Current/Best: 10.32/ 17.22 GFLOPS | Progress: (8/20) | 5.91 s
[Task 3/25] Current/Best: 8.08/ 22.24 GFLOPS | Progress: (12/20) | 7.85 s
[Task 3/25] Current/Best: 9.96/ 22.24 GFLOPS | Progress: (16/20) | 10.34 s
[Task 3/25] Current/Best: 7.39/ 22.24 GFLOPS | Progress: (20/20) | 12.51 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 5.17/ 8.53 GFLOPS | Progress: (4/20) | 6.42 s
[Task 4/25] Current/Best: 3.98/ 11.33 GFLOPS | Progress: (8/20) | 15.08 s
[Task 4/25] Current/Best: 12.45/ 12.45 GFLOPS | Progress: (12/20) | 26.43 s
[Task 4/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (16/20) | 29.09 s
[Task 4/25] Current/Best: 15.62/ 19.95 GFLOPS | Progress: (20/20) | 34.21 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.42/ 17.88 GFLOPS | Progress: (4/20) | 3.25 s
[Task 5/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (8/20) | 4.80 s
[Task 5/25] Current/Best: 9.13/ 20.72 GFLOPS | Progress: (12/20) | 6.59 s
[Task 5/25] Current/Best: 19.09/ 20.72 GFLOPS | Progress: (16/20) | 8.24 s
[Task 5/25] Current/Best: 13.56/ 22.95 GFLOPS | Progress: (20/20) | 10.33 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 15.33/ 15.33 GFLOPS | Progress: (4/20) | 5.19 s
[Task 6/25] Current/Best: 12.54/ 18.63 GFLOPS | Progress: (8/20) | 7.51 s
[Task 6/25] Current/Best: 14.42/ 18.63 GFLOPS | Progress: (12/20) | 10.46 s
[Task 6/25] Current/Best: 13.82/ 18.63 GFLOPS | Progress: (16/20) | 12.35 s
[Task 6/25] Current/Best: 11.40/ 18.63 GFLOPS | Progress: (20/20) | 17.84 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 14.09/ 14.09 GFLOPS | Progress: (4/20) | 3.66 s
[Task 7/25] Current/Best: 19.49/ 19.49 GFLOPS | Progress: (8/20) | 5.42 s
[Task 7/25] Current/Best: 11.42/ 20.28 GFLOPS | Progress: (12/20) | 8.14 s
[Task 7/25] Current/Best: 11.77/ 20.28 GFLOPS | Progress: (16/20) | 10.41 s
[Task 7/25] Current/Best: 22.44/ 22.44 GFLOPS | Progress: (20/20) | 12.13 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 13.23/ 13.23 GFLOPS | Progress: (4/20) | 4.69 s
[Task 8/25] Current/Best: 13.52/ 13.52 GFLOPS | Progress: (8/20) | 11.51 s
[Task 8/25] Current/Best: 4.55/ 14.06 GFLOPS | Progress: (12/20) | 15.09 s
[Task 8/25] Current/Best: 6.52/ 18.50 GFLOPS | Progress: (16/20) | 18.11 s
[Task 8/25] Current/Best: 17.36/ 18.50 GFLOPS | Progress: (20/20) | 20.30 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 9.98/ 19.87 GFLOPS | Progress: (4/20) | 5.29 s
[Task 9/25] Current/Best: 9.25/ 19.87 GFLOPS | Progress: (8/20) | 10.82 s
[Task 9/25] Current/Best: 12.58/ 19.87 GFLOPS | Progress: (12/20) | 21.66 s
[Task 9/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (16/20) | 32.53 s
[Task 9/25] Current/Best: 12.71/ 19.95 GFLOPS | Progress: (20/20) | 39.64 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 10.68/ 12.27 GFLOPS | Progress: (4/20) | 4.83 s
[Task 10/25] Current/Best: 8.59/ 20.55 GFLOPS | Progress: (8/20) | 6.58 s
[Task 10/25] Current/Best: 9.97/ 20.55 GFLOPS | Progress: (12/20) | 8.38 s
[Task 10/25] Current/Best: 16.27/ 20.55 GFLOPS | Progress: (16/20) | 10.06 s
[Task 10/25] Current/Best: 5.47/ 20.61 GFLOPS | Progress: (20/20
) | 11.48 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 21.33/ 21.33 GFLOPS | Progress: (4/20) | 3.88 s
[Task 11/25] Current/Best: 5.06/ 21.33 GFLOPS | Progress: (8/20) | 6.18 s
[Task 11/25] Current/Best: 23.05/ 23.05 GFLOPS | Progress: (12/20) | 8.08 s
[Task 11/25] Current/Best: 12.28/ 23.05 GFLOPS | Progress: (16/20) | 10.67 s
[Task 11/25] Current/Best: 12.46/ 23.05 GFLOPS | Progress: (20/20) | 12.86 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 11.50/ 11.50 GFLOPS | Progress: (4/20) | 6.20 s
[Task 12/25] Current/Best: 15.55/ 15.55 GFLOPS | Progress: (8/20) | 12.29 s
[Task 12/25] Current/Best: 18.45/ 18.45 GFLOPS | Progress: (12/20) | 14.65 s
[Task 12/25] Current/Best: 7.00/ 18.45 GFLOPS | Progress: (16/20) | 18.25 s
[Task 12/25] Current/Best: 15.14/ 18.45 GFLOPS | Progress: (20/20) | 21.18 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 5.77/ 17.33 GFLOPS | Progress: (4/20) | 4.17 s
[Task 13/25] Current/Best: 16.83/ 19.98 GFLOPS | Progress: (8/20) | 7.84 s
[Task 13/25] Current/Best: 15.96/ 19.98 GFLOPS | Progress: (12/20) | 10.32 s
[Task 13/25] Current/Best: 16.87/ 22.40 GFLOPS | Progress: (16/20) | 13.63 s
[Task 13/25] Current/Best: 11.94/ 22.40 GFLOPS | Progress: (20/20) | 16.14 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.23/ 15.57 GFLOPS | Progress: (4/20) | 5.30 s
[Task 14/25] Current/Best: 10.98/ 15.57 GFLOPS | Progress: (8/20) | 10.12 s
[Task 14/25] Current/Best: 13.30/ 15.57 GFLOPS | Progress: (12/20) | 12.56 s
[Task 14/25] Current/Best: 8.43/ 16.54 GFLOPS | Progress: (16/20) | 17.84 s Done.
+
[Task 14/25] Current/Best: 15.22/ 16.54 GFLOPS | Progress: (20/20) | 20.98 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.15/ 16.63 GFLOPS | Progress: (4/20) | 4.14 s
[Task 15/25] Current/Best: 8.77/ 18.17 GFLOPS | Progress: (8/20) | 5.57 s
[Task 15/25] Current/Best: 11.76/ 18.17 GFLOPS | Progress: (12/20) | 7.03 s
[Task 15/25] Current/Best: 5.16/ 18.17 GFLOPS | Progress: (16/20) | 13.37 s
[Task 15/25] Current/Best: 9.93/ 18.27 GFLOPS | Progress: (20/20) | 14.66 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 17.18/ 19.29 GFLOPS | Progress: (4/20) | 3.30 s
[Task 16/25] Current/Best: 6.16/ 19.29 GFLOPS | Progress: (8/20) | 6.90 s
[Task 16/25] Current/Best: 21.48/ 21.48 GFLOPS | Progress: (12/20) | 8.15 s
[Task 16/25] Current/Best: 7.48/ 21.48 GFLOPS | Progress: (16/20) | 11.33 s
[Task 16/25] Current/Best: 14.15/ 21.48 GFLOPS | Progress: (20/20) | 14.36 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.49/ 23.50 GFLOPS | Progress: (4/20) | 3.45 s
[Task 17/25] Current/Best: 21.38/ 23.50 GFLOPS | Progress: (8/20) | 5.70 s
[Task 17/25] Current/Best: 18.95/ 23.50 GFLOPS | Progress: (12/20) | 7.59 s
[Task 17/25] Current/Best: 11.17/ 23.50 GFLOPS | Progress: (16/20) | 10.91 s
[Task 17/25] Current/Best: 3.09/ 23.50 GFLOPS | Progress: (20/20) | 13.80 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.89/ 12.18 GFLOPS | Progress: (4/20) | 4.21 s
[Task 18/25] Current/Best: 4.76/ 22.28 GFLOPS | Progress: (8/20) | 6.97 s
[Task 18/25] Current/Best: 5.91/ 22.28 GFLOPS | Progress: (12/20) | 10.55 s
[Task 18/25] Current/Best: 11.91/ 22.28 GFLOPS | Progress: (16/20) | 13.43 s
[Task 18/25] Current/Best: 17.53/ 22.28 GFLOPS | Progress: (20/20) | 19.59 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 9.97/ 22.56 GFLOPS | Progress: (4/20) | 5.57 s
[Task 19/25] Current/Best: 7.81/ 22.56 GFLOPS | Progress: (8/20) | 8.15 s
[Task 19/25] Current/Best: 10.83/ 22.56 GFLOPS | Progress: (12/20) | 11.33 s
[Task 19/25] Current/Best: 10.98/ 22.56 GFLOPS | Progress: (16/20) | 15.19 s
[Task 19/25] Current/Best: 2.70/ 22.56 GFLOPS | Progress: (20/20) | 19.04 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 14.00/ 18.18 GFLOPS | Progress: (4/20) | 3.41 s
[Task 20/25] Current/Best: 7.46/ 18.18 GFLOPS | Progress: (8/20) | 7.16 s
[Task 20/25] Current/Best: 6.57/ 18.18 GFLOPS | Progress: (12/20) | 9.30 s
[Task 20/25] Current/Best: 16.41/ 18.18 GFLOPS | Progress: (16/20) | 13.14 s
[Task 20/25] Current/Best: 9.12/ 18.18 GFLOPS | Progress: (20/20) | 16.04 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 5.05/ 23.10 GFLOPS | Progress: (4/20) | 3.63 s
[Task 21/25] Current/Best: 4.73/ 23.10 GFLOPS | Progress: (8/20) | 5.58 s
[Task 21/25] Current/Best: 14.92/ 23.10 GFLOPS | Progress: (12/20) | 7.79 s
[Task 21/25] Current/Best: 10.24/ 23.10 GFLOPS | Progress: (16/20) | 11.74 s Done.
+
[Task 21/25] Current/Best: 11.98/ 23.10 GFLOPS | Progress: (20/20) | 13.66 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 12.21/ 15.35 GFLOPS | Progress: (4/20) | 3.79 s
[Task 22/25] Current/Best: 9.81/ 18.69 GFLOPS | Progress: (8/20) | 6.97 s
[Task 22/25] Current/Best: 6.16/ 18.69 GFLOPS | Progress: (12/20) | 8.40 s
[Task 22/25] Current/Best: 8.90/ 19.81 GFLOPS | Progress: (16/20) | 10.29 s
[Task 22/25] Current/Best: 7.16/ 20.11 GFLOPS | Progress: (20/20) | 11.92 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 21.14/ 22.60 GFLOPS | Progress: (4/20) | 6.46 s
[Task 23/25] Current/Best: 19.49/ 22.60 GFLOPS | Progress: (8/20) | 10.31 s
[Task 23/25] Current/Best: 9.86/ 22.60 GFLOPS | Progress: (12/20) | 13.26 s
[Task 23/25] Current/Best: 6.14/ 22.60 GFLOPS | Progress: (16/20) | 15.59 s
[Task 23/25] Current/Best: 10.79/ 22.60 GFLOPS | Progress: (20/20) | 17.67 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.86/ 8.79 GFLOPS | Progress: (4/20) | 2.86 s
[Task 24/25] Current/Best: 0.58/ 8.79 GFLOPS | Progress: (8/20) | 6.13 s
[Task 24/25] Current/Best: 3.81/ 8.79 GFLOPS | Progress: (12/20) | 16.87 s
[Task 24/25] Current/Best: 3.49/ 10.45 GFLOPS | Progress: (16/20) | 27.34 s
[Task 24/25] Current/Best: 7.03/ 10.45 GFLOPS | Progress: (20/20) | 34.09 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 3.46/ 9.69 GFLOPS | Progress: (4/20) | 4.66 s
[Task 25/25] Current/Best: 6.06/ 9.69 GFLOPS | Progress: (8/20) | 11.14 s
[Task 25/25] Current/Best: 6.91/ 9.69 GFLOPS | Progress: (12/20) | 21.89 s
[Task 25/25] Current/Best: 3.51/ 9.69 GFLOPS | Progress: (16/20) | 32.62 s
[Task 25/25] Current/Best: 5.78/ 9.69 GFLOPS | Progress: (20/20) | 43.32 s
@@ -673,8 +672,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621105
- class='n02123159 tiger cat' with probability=0.356377
+ class='n02123045 tabby, tabby cat' with probability=0.621102
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -731,8 +730,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 417.815636309997, 'median': 417.1192714999961, 'std': 4.3123419468717845}
- unoptimized: {'mean': 513.8065643800019, 'median': 513.9278934999766, 'std': 1.6299110458413983}
+ optimized: {'mean': 401.1140108500149, 'median': 399.01219244998174, 'std': 4.410206059196968}
+ unoptimized: {'mean': 514.875446879978, 'median': 515.1379385999917, 'std': 1.4243465931917811}
@@ -755,7 +754,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 32.481 seconds)
+ **Total running time of the script:** ( 11 minutes 21.271 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 e663074443..9ca1ed0cd4 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
- 1.265e-07 secs/op
+ 2.242e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index fa5fed3df2..649c4cf4d4 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, 0x1294ce60)), stage(b, placeholder(b, 0x15ece6f0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x9d3de00)), stage(b, placeholder(b, 0x23defe70)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index af3fee118e..5a92ad92a5 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
=================
-**14:10.266** total execution time for **tutorial** files:
+**15:11.349** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:32.481 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:21.271 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:36.868 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:43.051 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.493 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.781 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.249 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.328 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:21.692 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:28.083 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.772 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.841 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.541 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.776 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.163 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.208 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index de4a428d91..c27172069c 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.87341999966884e-06 1.0
- naive 6.7052e-06 0.8516248339707553
- parallel 6.9386e-06 0.8812688768402855
- vector 2.4577299999999996e-05 3.12155327685221
+ numpy 7.782479997331393e-06 1.0
+ naive 7.4378e-06 0.955710776327137
+ parallel 6.954899999999999e-06 0.8936611468818204
+ vector 2.4541199999999998e-05 3.153390694022363
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018552
+ Numpy running time: 0.019019
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.438324
+ none: 3.381993
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.302397
+ blocking: 0.302984
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.340223
+ vectorization: 0.342094
@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: 0.115306
+ loop permutation: 0.118003
@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: 0.107714
+ array packing: 0.108422
@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: 0.110911
+ block caching: 0.110895
@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: 0.146020
+ parallelization: 0.146388
@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 3.4383240071000003 1.0
- blocking 0.3023969382 0.08794893604429442
- vectorization 0.3402233243 0.09895033847812265
- loop permutation 0.11530623439999999 0.03353559296968443
- array packing 0.10771403859999999 0.03132748349997698
- block caching 0.11091117549999999 0.0322573367928598
- parallelization 0.14601966859999999 0.042468268929418886
+ none 3.3819934623999997 1.0
+ blocking 0.3029840328 0.08958740936920388
+ vectorization 0.34209401229999997 0.10115158887895549
+ loop permutation 0.1180031295 0.0348915900671967
+ array packing 0.10842177719999999 0.03205854133232401
+ block caching 0.1108952911 0.03278991882536172
+ parallelization 0.1463876009 0.04328441273689436
@@ -1663,7 +1663,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.493 seconds)
+ **Total running time of the script:** ( 1 minutes 0.781 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index b5b7070f38..8046ba6160 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-f950b118aa96cd2c14b02104defd78107403c9f1
+a15663654b4edcefa6431a1c3fb033069d17bc71
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index a366361f1a..81ce932d95 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 12.775 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.452 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 08a136df64..b1bb52252b 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 936ms/step
+1/1 [==============================] - 1s 958ms/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 4c93fabe1b..bdcb897d16 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.zip29f59305-b4d0-4083-a467-7a6bf694e52a 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.zipc1754c42-830c-451e-921c-9a3cab227639 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 da1373a886..c857224d6b 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,13 +448,14 @@ 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]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 64.2MB/s]
- 30%|### | 12.5M/41.5M [00:00<00:00, 57.7MB/s]
- 43%|####3 | 18.0M/41.5M [00:00<00:00, 31.4MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 32.4MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 42.3MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 42.4MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 41.5MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 61.1MB/s]
+ 29%|##9 | 12.2M/41.5M [00:00<00:00, 52.5MB/s]
+ 42%|####1 | 17.2M/41.5M [00:00<00:00, 42.8MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 41.8MB/s]
+ 64%|######3 | 26.4M/41.5M [00:00<00:00, 35.0MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.1MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 37.1MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 40.5MB/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 51bdc2bea8..b53137d4bd 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,13 +431,10 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 44.4MB/s]
- 36%|###5 | 16.0M/44.7M [00:00<00:00, 49.2MB/s]
- 54%|#####3 | 24.0M/44.7M [00:00<00:00, 57.2MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 57.0MB/s]
- 86%|########5 | 38.3M/44.7M [00:00<00:00, 59.4MB/s]
- 99%|#########8| 44.1M/44.7M [00:00<00:00, 49.7MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 52.8MB/s]
+ 14%|#4 | 6.30M/44.7M [00:00<00:00, 42.9MB/s]
+ 50%|##### | 22.5M/44.7M [00:00<00:00, 104MB/s]
+ 93%|#########3| 41.6M/44.7M [00:00<00:00, 143MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 121MB/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 3560537ebf..9fa4779b75 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 11.116 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.860 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 66700efb98..39da6fc694 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>05:48.655</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:55.502</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_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>01:12.775</p></td>
+<td><p>01:14.452</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>01:11.116</p></td>
+<td><p>01:11.860</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>00:45.891</p></td>
+<td><p>00:46.861</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:33.171</p></td>
+<td><p>00:34.250</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:29.684</p></td>
+<td><p>00:31.197</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>00:26.251</p></td>
+<td><p>00:27.013</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:26.086</p></td>
+<td><p>00:25.648</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>00:22.867</p></td>
+<td><p>00:23.729</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>00:18.413</p></td>
+<td><p>00:18.083</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>00:02.401</p></td>
+<td><p>00:02.409</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 42de0a12b1..1415755a4c 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)
- 16.0904 16.0779 16.2258 15.9644 0.0912
+ 16.0995 16.0965 16.2038 15.9310 0.0747
</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 bce7463c10..e219696666 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,21 +453,23 @@ 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]
- 8%|7 | 13.5M/170M [00:00<00:01, 142MB/s]
- 16%|#5 | 27.1M/170M [00:00<00:01, 98.9MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:01, 84.7MB/s]
- 33%|###2 | 56.0M/170M [00:00<00:01, 105MB/s]
- 40%|#### | 68.4M/170M [00:00<00:00, 112MB/s]
- 47%|####6 | 79.8M/170M [00:00<00:00, 108MB/s]
- 53%|#####3 | 90.5M/170M [00:00<00:00, 95.8MB/s]
- 61%|######1 | 104M/170M [00:01<00:00, 101MB/s]
- 67%|######7 | 114M/170M [00:01<00:00, 102MB/s]
- 73%|#######2 | 124M/170M [00:01<00:00, 97.4MB/s]
- 80%|######## | 136M/170M [00:01<00:00, 104MB/s]
- 87%|########6 | 148M/170M [00:01<00:00, 109MB/s]
- 93%|#########3| 158M/170M [00:01<00:00, 108MB/s]
- 99%|#########9| 169M/170M [00:01<00:00, 88.4MB/s]
-100%|##########| 170M/170M [00:01<00:00, 99.9MB/s]
+ 5%|4 | 7.68M/170M [00:00<00:02, 61.5MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 74.4MB/s]
+ 14%|#3 | 23.2M/170M [00:00<00:02, 68.6MB/s]
+ 18%|#7 | 29.9M/170M [00:00<00:02, 62.2MB/s]
+ 21%|##1 | 35.9M/170M [00:00<00:02, 62.2MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:01, 73.8MB/s]
+ 35%|###5 | 59.6M/170M [00:00<00:01, 87.5MB/s]
+ 44%|####3 | 74.1M/170M [00:01<00:01, 73.9MB/s]
+ 48%|####8 | 81.7M/170M [00:01<00:01, 75.2MB/s]
+ 55%|#####5 | 94.2M/170M [00:01<00:00, 88.8MB/s]
+ 61%|###### | 103M/170M [00:01<00:00, 88.5MB/s]
+ 66%|######6 | 112M/170M [00:01<00:00, 82.8MB/s]
+ 71%|#######1 | 121M/170M [00:01<00:00, 86.2MB/s]
+ 78%|#######8 | 133M/170M [00:01<00:00, 77.6MB/s]
+ 87%|########6 | 148M/170M [00:01<00:00, 95.1MB/s]
+ 93%|#########2| 157M/170M [00:02<00:00, 77.0MB/s]
+100%|##########| 170M/170M [00:02<00:00, 81.6MB/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=& [...]
@@ -565,7 +567,7 @@ 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 14.467 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 19.195 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 b8a75f9853..0d15b34d04 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, 57.5MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 80.0MB/s]
+ 51%|##### | 6.90M/13.6M [00:00<00:00, 72.3MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 47.3MB/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)
- 90.2063 90.0435 94.8826 89.8450 0.5534
+ 90.5402 90.5235 91.2512 90.1183 0.2587
</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 5.534 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.441 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 ba6259280b..1145a5bc02 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)
- 117.4192 117.1418 121.0319 115.9212 1.0907
+ 120.7630 120.7308 125.6918 119.9436 0.6827
</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 21.628 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 29.523 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 602af19fbe..b5c8481d1e 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 39.367 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.375 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 6781eda668..634bf1c016 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,26 +462,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 1%| | 881/132723 [00:00<00:14, 8804.01KB/s]
- 6%|5 | 7804/132723 [00:00<00:02, 44336.03KB/s]
- 12%|#1 | 15455/132723 [00:00<00:01, 59022.20KB/s]
- 17%|#7 | 23064/132723 [00:00<00:01, 65757.44KB/s]
- 22%|##2 | 29641/132723 [00:00<00:01, 61812.46KB/s]
- 27%|##7 | 35861/132723 [00:00<00:01, 56278.45KB/s]
- 33%|###2 | 43513/132723 [00:00<00:01, 62298.38KB/s]
- 39%|###8 | 51234/132723 [00:00<00:01, 66714.85KB/s]
- 44%|####4 | 58945/132723 [00:00<00:01, 69816.59KB/s]
- 50%|##### | 66625/132723 [00:01<00:00, 71904.08KB/s]
- 56%|#####5 | 74315/132723 [00:01<00:00, 73398.29KB/s]
- 62%|######1 | 81905/132723 [00:01<00:00, 68575.83KB/s]
- 67%|######7 | 89516/132723 [00:01<00:00, 70708.47KB/s]
- 73%|#######3 | 97235/132723 [00:01<00:00, 72576.09KB/s]
- 79%|#######8 | 104562/132723 [00:01<00:00, 68139.62KB/s]
- 84%|########3 | 111471/132723 [00:01<00:00, 64892.33KB/s]
- 89%|########8 | 118044/132723 [00:01<00:00, 62325.26KB/s]
- 95%|#########4| 125718/132723 [00:01<00:00, 66265.19KB/s]
-100%|#########9| 132428/132723 [00:02<00:00, 64770.96KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 64741.57KB/s]
+ 5%|4 | 6384/132723 [00:00<00:01, 63834.43KB/s]
+ 11%|#1 | 14877/132723 [00:00<00:01, 76237.41KB/s]
+ 17%|#6 | 22501/132723 [00:00<00:01, 73641.01KB/s]
+ 23%|##3 | 30988/132723 [00:00<00:01, 77977.35KB/s]
+ 29%|##9 | 38802/132723 [00:00<00:01, 71845.13KB/s]
+ 36%|###5 | 47245/132723 [00:00<00:01, 75852.64KB/s]
+ 42%|####1 | 55713/132723 [00:00<00:00, 78611.30KB/s]
+ 48%|####8 | 64161/132723 [00:00<00:00, 80422.36KB/s]
+ 55%|#####4 | 72582/132723 [00:00<00:00, 81578.67KB/s]
+ 61%|######1 | 81128/132723 [00:01<00:00, 82757.95KB/s]
+ 68%|######7 | 89607/132723 [00:01<00:00, 83370.21KB/s]
+ 74%|#######3 | 98208/132723 [00:01<00:00, 84165.99KB/s]
+ 80%|######## | 106639/132723 [00:01<00:00, 69143.37KB/s]
+ 87%|########6 | 115054/132723 [00:01<00:00, 73061.76KB/s]
+ 93%|#########3| 123563/132723 [00:01<00:00, 76328.44KB/s]
+ 99%|#########9| 131917/132723 [00:01<00:00, 78341.77KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 77343.86KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -520,7 +517,7 @@ 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 56.256 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 3.896 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 4577f0c29c..c7bdeca329 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>12:43.999</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:10.505</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:14.467</p></td>
+<td><p>03:19.195</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>02:56.256</p></td>
+<td><p>03:03.896</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>02:21.628</p></td>
+<td><p>02:29.523</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>01:39.367</p></td>
+<td><p>01:42.375</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>01:05.534</p></td>
+<td><p>01:07.441</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>00:36.547</p></td>
+<td><p>00:36.611</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>00:25.389</p></td>
+<td><p>00:26.026</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>00:24.804</p></td>
+<td><p>00:25.431</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 801563cca6..aeb70ff47b 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.zipd6fccdbd-a516-473d-9bbe-c59cb1199ecd 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.zipfbd1211b-7e7d-4aa4-9bf7-36ba6ef28a7c 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 96c9c1d1a3..4c1841a655 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>00:46.120</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.147</strong> total execution time for <strong>how_to_extend_tvm</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="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>00:42.745</p></td>
+<td><p>00:42.791</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>00:02.360</p></td>
+<td><p>00:02.351</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>00:01.007</p></td>
+<td><p>00:00.997</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index c3f187641c..27ef4409b5 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: 7138us [7138us] (46.33%; 46.33%)
-FoldScaleAxis: 8269us [6us] (53.67%; 53.67%)
- FoldConstant: 8263us [1700us] (53.63%; 99.92%)
- InferType: 6563us [6563us] (42.60%; 79.43%)
+InferType: 7104us [7104us] (46.53%; 46.53%)
+FoldScaleAxis: 8163us [6us] (53.47%; 53.47%)
+ FoldConstant: 8157us [1676us] (53.43%; 99.92%)
+ InferType: 6481us [6481us] (42.45%; 79.45%)
</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: 6659us [6659us] (45.23%; 45.23%)
-FoldScaleAxis: 8065us [5us] (54.77%; 54.77%)
- FoldConstant: 8060us [1689us] (54.74%; 99.94%)
- InferType: 6371us [6371us] (43.27%; 79.04%)
+InferType: 6487us [6487us] (44.94%; 44.94%)
+FoldScaleAxis: 7947us [4us] (55.06%; 55.06%)
+ FoldConstant: 7942us [1639us] (55.03%; 99.94%)
+ InferType: 6303us [6303us] (43.67%; 79.36%)
</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 09993a5d15..0aa15fed47 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: 54.211456 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.210494 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 64f2571087..8d1a0c3a78 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: 13.069337 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.363360 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 dac8022eb3..dea2e92274 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: 0.017787
-Baseline: 3.315946
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019615
+Baseline: 3.374956
</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: 0.297152
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296781
</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: 0.329254
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.339034
</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: 0.112337
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118282
</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: 0.108558
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109400
</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: 0.110090
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111530
</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: 0.146061
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147527
</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 671f8a70c8..4ce8e758fd 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>00:34.306</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.206</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>00:31.695</p></td>
+<td><p>00:32.409</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>00:01.496</p></td>
+<td><p>00:01.580</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>00:01.115</p></td>
+<td><p>00:01.218</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 64868611eb..fb717d6357 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:02.077</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:10.863</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:37.178</p></td>
+<td><p>05:39.472</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>01:31.395</p></td>
+<td><p>01:33.187</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:02.337</p></td>
+<td><p>01:04.157</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>00:28.690</p></td>
+<td><p>00:31.162</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>00:11.596</p></td>
+<td><p>00:11.785</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>00:10.881</p></td>
+<td><p>00:11.099</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 39de05017a..b9b87543fb 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
@@ -504,382 +504,184 @@ 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" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ 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, [9216]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 16) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
let cse_var_1: int32 = (rc.outer.outer*288)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 96), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*27)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 1)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 2)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 6)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 3)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 5)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 4)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 4)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 5)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 3)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 6)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 2)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 7)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 3)), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) - 1)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 8)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 9)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 10)] = data[(((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21))]
- pad_temp.shared_1[((threadIdx.x_1*27) + 11)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 1)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 12)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 2)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 13)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 3)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 14)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 4)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 15)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 5)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 16)] = data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 6)]
- pad_temp.shared_1[((threadIdx.x_1*27) + 17)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 18)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*27) + 19)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 20)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 21)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 9)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 22)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 10)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 23)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 11)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 24)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 12)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 25)] = @tir.if_then_else((floormod(threadIdx.x_1, 3) < 2), data[((((rc.outer.outer*1568) + (floordiv(threadIdx.x_1, 3)*49)) + (floormod(threadIdx.x_1, 3)*21)) + 13)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*27) + 26)] = 0f32
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[(threadIdx.x_1*6)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*2), 27)) && (floormod((threadIdx.x_1*6), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 27)*49)) + (floordiv(floormod((threadIdx.x_1*2), 27), 3)*7)) + floormod((threadIdx.x_1*6), 9)) - 8) [...]
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*2), 27)) && (floormod(((threadIdx.x_1*6) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 27)*49)) + (floordiv(floormod((threadIdx.x_1*2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*2), 27)) && (floormod(((threadIdx.x_1*6) + 2), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 27)*49)) + (floordiv(floormod((threadIdx.x_1*2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 3), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 5), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 112), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1008), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3024), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3248), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3360), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3472), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3584), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3696), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3808), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4144), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4256), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4368), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4480), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4592), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4704), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4816)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4816), 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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4928), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5040)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5040), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5152)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5152), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5264)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5264), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5376), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5488)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5488), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5600)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5600), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5712)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5712), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5824), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 5936)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5936), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6048)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6160)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6160), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6272)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6272), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6384)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6384), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6496)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6496), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6608)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6608), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6720)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6720), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6832)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6832), 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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 6944)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6944), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7056)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7056), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7168), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7280), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7392), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7504)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7504), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7616)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7616), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7728)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7728), 288)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 80), 96)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7840), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 7952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 7952), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8064)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8176)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8176), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8288)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8288), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8400)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8400), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8512)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8512), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8624)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8624), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 272), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8736)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8736), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8848)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8848), 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" = 112;
- kernel.shared_1[(threadIdx.x_2 + 8960)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 8960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 9072)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 9072), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 9184)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 9184), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1176)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 14), 27)) && (floormod(((threadIdx.x_1*6) + 42), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1177)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 14), 27)) && (floormod(((threadIdx.x_1*6) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype= [...]
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1178)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 14), 27)) && (floormod(((threadIdx.x_1*6) + 44), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1179)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)) && (floormod(((threadIdx.x_1*6) + 45), 81) < 72)) && (1 < floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 27)*49)) + (floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1180)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)) && (floormod(((threadIdx.x_1*6) + 46), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 27)*49)) + (floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f3 [...]
+ pad_temp.shared_1[((threadIdx.x_1*6) + 1181)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)) && (floormod(((threadIdx.x_1*6) + 47), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 27)*49)) + (floormod((floordiv((threadIdx.x_1*2), 3) + 5), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32 [...]
}
- for (rc.outer.inner: int32, 0, 4) {
- for (xx.outer.inner: int32, 0, 7) {
- let cse_var_2: int32 = (xx.outer.inner + 7)
- {
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72))]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[(((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4608)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 1)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4609)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 2)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4610)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 3)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4611)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4612)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 5)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4613)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 6)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4614)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 7)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4615)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 8)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4616)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 9)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4617)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 10)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4618)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 11)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4619)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 12)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4620)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 13)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4621)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 14)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4622)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 15)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4623)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 16)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4624)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 17)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4625)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 18)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4626)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 19)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4627)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 20)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4628)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 21)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4629)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 22)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4630)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 23)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4631)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 24)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4632)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 25)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4633)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 26)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4634)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 27)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4635)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 28)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4636)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 29)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4637)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 30)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4638)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 31)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4639)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 32)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4640)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 33)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4641)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 34)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4642)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 35)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4643)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 36)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4644)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 37)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4645)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 38)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4646)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 39)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4647)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 40)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 334)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4648)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 41)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 335)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4649)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 42)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4650)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 43)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4651)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 44)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4652)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 45)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4653)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 46)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4654)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 47)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4655)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 48)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4656)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 49)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 415)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4657)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 50)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 416)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4658)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 51)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4659)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 52)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 424)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4660)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 53)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 425)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4661)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 54)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4662)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 55)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4663)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 56)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4664)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 57)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4665)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 58)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 496)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4666)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 59)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 497)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4667)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 60)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4668)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 61)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 505)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4669)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 62)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 506)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4670)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 63)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4671)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 64)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4672)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 65)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4673)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 66)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4674)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 67)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 577)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4675)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 68)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 578)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4676)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 69)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4677)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 586)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 70)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 586)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4678)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 587)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 71)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 587)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + 4679)]))
- }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2352)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 3), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2353)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2354)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 1), 27)) && (floormod(((threadIdx.x_1*6) + 5), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 784), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2355)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 2), 27)) && (floormod(((threadIdx.x_1*6) + 6), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
}
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2356)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 2), 27)) && (floormod(((threadIdx.x_1*6) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 40), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*6) + 2357)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*2) + 2), 27)) && (floormod(((threadIdx.x_1*6) + 8), 81) < 72)) && (1 < floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 785), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*73728) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*73728) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1372), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 220), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1764), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2156), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2548), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 244), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2744), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2940), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3332), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3528), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3724), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 268), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4116), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4312), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 100), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4508), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 16) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2304)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 288)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2592)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2305)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 289)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2593)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2306)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 290)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2594)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2307)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 291)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2595)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2308)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 292)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2596)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2309)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 293)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2597)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2310)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 294)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2598)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2311)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 295)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2599)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2312)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 296)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2600)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2313)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 297)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2601)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2314)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 298)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2602)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2315)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 299)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2603)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2316)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 300)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2604)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2317)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 301)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2605)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2318)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 302)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2606)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2319)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 303)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2607)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2320)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 304)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2608)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2321)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 305)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (rc.outer.inner*18)) + 2609)]))
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner) + 784)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias[(((blockIdx.x*32) + floordiv(threadIdx.x, 7)) + 16)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
}
}
}
@@ -916,7 +718,7 @@ 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: 0.270 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.255 ms
</pre></div>
</div>
</div>
@@ -945,20 +747,20 @@ 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=1)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
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_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
@@ -967,14 +769,14 @@ s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nc
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -994,12 +796,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
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=27)
+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=6)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1019,293 +821,151 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
+extern "C" __global__ void __launch_bounds__(196) 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[9216];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 96) {
- pad_temp_shared[(((int)threadIdx.x) * 27)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 1)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 2)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 3)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 5)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 4)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 4)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 5)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 3)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 6)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 2)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 7)] = ((1 <= (((int)threadIdx.x) % 3)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) - 1)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 8)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 9)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 10)] = data[(((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21))];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 11)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 1)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 12)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 2)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 13)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 3)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 14)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 4)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 15)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 5)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 16)] = data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 6)];
- pad_temp_shared[((((int)threadIdx.x) * 27) + 17)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 18)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 27) + 19)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 20)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 21)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 9)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 22)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 10)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 23)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 11)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 24)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 12)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 25)] = (((((int)threadIdx.x) % 3) < 2) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 3) * 49)) + ((((int)threadIdx.x) % 3) * 21)) + 13)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 27) + 26)] = 0.000000e+00f;
+ pad_temp_shared[(((int)threadIdx.x) * 6)] = (((((3 <= ((((int)threadIdx.x) * 2) % 27)) && (((((int)threadIdx.x) * 6) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 27) * 49)) + ((((((int)threadIdx.x) * 2) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1)] = (((((3 <= ((((int)threadIdx.x) * 2) % 27)) && ((((((int)threadIdx.x) * 6) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 27) * 49)) + ((((((int)threadIdx.x) * 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2)] = (((((3 <= ((((int)threadIdx.x) * 2) % 27)) && ((((((int)threadIdx.x) * 6) + 2) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 27) * 49)) + ((((((int)threadIdx.x) * 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 3)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 3) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 4)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 5)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 5) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1176)] = (((((3 <= (((((int)threadIdx.x) * 2) + 14) % 27)) && ((((((int)threadIdx.x) * 6) + 42) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 392) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1177)] = (((((3 <= (((((int)threadIdx.x) * 2) + 14) % 27)) && ((((((int)threadIdx.x) * 6) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 392) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1178)] = (((((3 <= (((((int)threadIdx.x) * 2) + 14) % 27)) && ((((((int)threadIdx.x) * 6) + 44) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 392) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1179)] = (((((1 <= ((((((int)threadIdx.x) * 2) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 6) + 45) % 81) < 72)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 393) / 27) * 49)) + (((((((int)threadIdx.x) * 2) / 3) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1180)] = (((((1 <= ((((((int)threadIdx.x) * 2) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 6) + 46) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 393) / 27) * 49)) + (((((((int)threadIdx.x) * 2) / 3) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 1181)] = (((((1 <= ((((((int)threadIdx.x) * 2) / 3) + 5) % 9)) && ((((((int)threadIdx.x) * 6) + 47) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 393) / 27) * 49)) + (((((((int)threadIdx.x) * 2) / 3) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2352)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 3) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2353)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2354)] = (((((3 <= (((((int)threadIdx.x) * 2) + 1) % 27)) && ((((((int)threadIdx.x) * 6) + 5) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 784) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3248) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3472) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3696) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4144) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4368) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4592) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4704) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 4816)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4816) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4928) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5040)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5040) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5152) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5264)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5264) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5376) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5488)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5488) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5600) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5712)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5712) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5824) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 5936)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5936) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 6160)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6160) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6272) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6384)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6384) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 6496)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6496) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6608)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6608) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6720)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6720) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 6832)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6832) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 6944)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6944) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7056)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7056) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7168) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7280) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7392) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7504)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7504) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7616)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7616) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7728)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7728) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 80) % 96) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7840) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 7952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 7952) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 8176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8176) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8288)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8288) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 224) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8400)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8400) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 8512)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8512) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 160) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8624)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8624) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 272) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8736)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8736) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 96)];
- kernel_shared[(((int)threadIdx.x) + 8848)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8848) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 8960) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 9072)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 9072) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 144)];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 9184)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 9184) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 256) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2355)] = (((((3 <= (((((int)threadIdx.x) * 2) + 2) % 27)) && ((((((int)threadIdx.x) * 6) + 6) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2356)] = (((((3 <= (((((int)threadIdx.x) * 2) + 2) % 27)) && ((((((int)threadIdx.x) * 6) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[((((int)threadIdx.x) * 6) + 2357)] = (((((3 <= (((((int)threadIdx.x) * 2) + 2) % 27)) && ((((((int)threadIdx.x) * 6) + 8) % 81) < 72)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 785) / 27) * 49)) + (((((((int)threadIdx.x) * 2) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 104) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 116) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 220) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 128) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 232) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 140) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 244) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 152) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 60)];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3332) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 164) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3528) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3724) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 268) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 176) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4116) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 84)];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4312) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 100) {
+ kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4508) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 188) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72))]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[(((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4608)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 1)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4609)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 2)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4610)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 3)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4611)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4612)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 5)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4613)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 6)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4614)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 7)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4615)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 8)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4616)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 9)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4617)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 10)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4618)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 11)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4619)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 12)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4620)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 13)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4621)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 14)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4622)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 15)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4623)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 16)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4624)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 17)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4625)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 18)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4626)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 19)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4627)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 20)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4628)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 21)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4629)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 22)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4630)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 23)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4631)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 24)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4632)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 25)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4633)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 26)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4634)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 27)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4635)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 28)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4636)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 29)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4637)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 30)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4638)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 31)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4639)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 32)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4640)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 33)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4641)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 34)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4642)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 35)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4643)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 36)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4644)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 37)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4645)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 38)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4646)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 39)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4647)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 40)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4648)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 41)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4649)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 42)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4650)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 43)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4651)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 44)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4652)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 45)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4653)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 46)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4654)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 47)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4655)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 48)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4656)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 49)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4657)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 50)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4658)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 51)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4659)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 52)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4660)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 53)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4661)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 54)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4662)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 55)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4663)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 56)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4664)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 57)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4665)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 58)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4666)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 59)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4667)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 60)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4668)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 61)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 505)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4669)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 62)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 506)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4670)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 63)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4671)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 64)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 568)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4672)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 65)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 569)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4673)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 66)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 576)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4674)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 67)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 577)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4675)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 68)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 578)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4676)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 69)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 585)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4677)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 586)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 70)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 586)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4678)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 587)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 71)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 648) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 587)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + 4679)]));
- }
+ 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) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2304)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 288)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2592)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2305)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 289)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2593)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2306)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 290)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2594)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2307)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 291)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2595)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2308)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 292)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2596)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2309)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 293)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2597)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2310)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 294)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2598)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2311)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 295)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2599)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2312)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 296)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2600)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2313)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 297)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2601)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2314)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 298)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2602)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2315)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 299)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2603)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2316)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 300)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2604)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2317)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 301)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2605)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2318)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 302)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2606)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2319)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 303)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2607)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2320)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 304)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2608)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2321)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 305)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (rc_outer_inner * 18)) + 2609)]));
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner) + 784)] = max((conv2d_nchw[(i3_inner + 7)] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7)) + 16)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1342,7 +1002,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 37.178 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 39.472 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 af2a175147..7614bd51aa 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)
- 8.1941 8.2051 8.2059 8.1713 0.0161
+ 8.1888 8.1820 8.2053 8.1790 0.0118
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.337 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.157 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 de4c708442..33863c0003 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)
- 757.9147 756.8484 762.4136 754.4822 3.3246
+ 745.9471 746.3612 746.7702 744.7098 0.8907
</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 31.395 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.187 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 5136c1f407..ed349e03ec 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,13 +632,13 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
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, 16) {
+ for (i.outer.inner: int32, 0, 2) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (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
@@ -659,11 +659,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
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, 8) {
+ for (i.inner: int32, 0, 64) {
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*2048) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (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)
@@ -741,7 +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: 1.861 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.857 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 40a79c9ab4..c2586fc796 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>00:43.608</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:50.049</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,22 +349,22 @@
</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>00:43.572</p></td>
+<td><p>00:50.014</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<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>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
+<tr class="row-odd"><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>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 a550496a1a..fc41c53c5d 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,9 +567,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 117.61/117.61 result: MeasureResult(costs=(0.0019684631967213117,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.218931436538696, timestamp=1668132414.1469023) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7292483
-No: 2 GFLOPS: 21.40/117.61 result: MeasureResult(costs=(0.0108182304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.342834711074829, timestamp=1668132414.8630574) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,485208
-No: 3 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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
@@ -691,163 +689,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9056115
-No: 4 GFLOPS: 2.58/117.61 result: MeasureResult(costs=(0.0898759765,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.753143072128296, timestamp=1668132417.2495856) [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,723215
-No: 5 GFLOPS: 9.71/117.61 result: MeasureResult(costs=(0.023840713500000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3782944679260254, timestamp=1668132419.5063689) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,855362
-No: 6 GFLOPS: 0.00/117.61 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 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, 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: 0x00007f7a550b6fa2
- 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, 32, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5269801
-No: 7 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8729037
+No: 2 GFLOPS: 0.00/0.00 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
@@ -969,8 +812,9 @@ 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, 8, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 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,1532117
-No: 8 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1351202
+No: 3 GFLOPS: 25.41/25.41 result: MeasureResult(costs=(0.009109318090909091,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7228238582611084, timestamp=1668134036.384868) [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6461748
+No: 4 GFLOPS: 0.00/25.41 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
@@ -1092,8 +936,8 @@ 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, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1001142
-No: 9 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1284068
+No: 5 GFLOPS: 0.00/25.41 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
@@ -1215,8 +1059,8 @@ 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, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1471325
-No: 10 GFLOPS: 0.00/117.61 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, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6876097
+No: 6 GFLOPS: 0.00/25.41 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
@@ -1338,8 +1182,8 @@ 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, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3224715
-No: 11 GFLOPS: 0.00/117.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1353577
+No: 7 GFLOPS: 0.00/25.41 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
@@ -1461,9 +1305,8 @@ 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, 128, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,256106
-No: 12 GFLOPS: 151.21/151.21 result: MeasureResult(costs=(0.001530953975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.975346326828003, timestamp=1668132427.996528) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8598500
-No: 13 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8320412
+No: 8 GFLOPS: 0.00/25.41 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
@@ -1585,8 +1428,8 @@ 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, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8883032
-No: 14 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6346876
+No: 9 GFLOPS: 0.00/25.41 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
@@ -1708,8 +1551,10 @@ 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, 32, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5164532
-No: 15 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1471435
+No: 10 GFLOPS: 8.60/25.41 result: MeasureResult(costs=(0.026912216,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.046284914016724, timestamp=1668134042.8115733) [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4875818
+No: 11 GFLOPS: 134.75/134.75 result: MeasureResult(costs=(0.0017180133050847457,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6454510688781738, timestamp=1668134043.4456222) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8335800
+No: 12 GFLOPS: 0.00/134.75 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
@@ -1831,284 +1676,10 @@ 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, 2, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6029674
-No: 16 GFLOPS: 0.00/151.21 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 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h: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:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h: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
-
-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:388
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h: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, 2, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10368315
-No: 17 GFLOPS: 0.00/151.21 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 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, 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: 0x00007f0ecb919fa2
- 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, 128, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5269987
-No: 18 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7218354
+No: 13 GFLOPS: 70.22/134.75 result: MeasureResult(costs=(0.0032966100303030306,), error_no=MeasureErrorNo.NO_ERROR, all_cost=10.126962900161743, timestamp=1668134053.7817192) [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9959905
+No: 14 GFLOPS: 10.27/134.75 result: MeasureResult(costs=(0.022534527999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7662863731384277, timestamp=1668134054.6339877) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8181689
+No: 15 GFLOPS: 0.00/134.75 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
@@ -2230,8 +1801,8 @@ 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, 8, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7570183
-No: 19 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8533089
+No: 16 GFLOPS: 0.00/134.75 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
@@ -2353,8 +1924,26 @@ 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, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2290340
-No: 20 GFLOPS: 0.00/151.21 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('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, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6771897
+No: 17 GFLOPS: 0.00/134.75 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3009218
+No: 18 GFLOPS: 0.00/134.75 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
@@ -2476,7 +2065,9 @@ 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, 2, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10021213
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8602196
+No: 19 GFLOPS: 1.63/134.75 result: MeasureResult(costs=(0.14215892025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.336716651916504, timestamp=1668134067.0871265) [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6583704
+No: 20 GFLOPS: 22.30/134.75 result: MeasureResult(costs=(0.010381638299999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6288275718688965, timestamp=1668134067.8301349) [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,233839
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2515,9 +2106,9 @@ 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8598500
+[('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8335800
Finish loading 20 records
-Time cost of this operator: 0.001748
+Time cost of this operator: 0.002147
</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 3ffa20c584..185cdf65e4 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -596,10 +596,10 @@ 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 311.1 98.727 (1, 2, 10, 10, 3) 2 1 [311.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.034 0.963 (1, 6, 10, 10) 1 1 [3.034]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.977 0.31 (1, 1, 10, 10, 3) 1 1 [0.977]
-Total_time - 315.11 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.5 98.713 (1, 2, 10, 10, 3) 2 1 [310.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.084 0.981 (1, 6, 10, 10) 1 1 [3.084]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.306 (1, 1, 10, 10, 3) 1 1 [0.963]
+Total_time - 314.547 - - - - -
</pre></div>
</div>
</div>
@@ -650,10 +650,10 @@ 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 100.2 97.308 (1, 6, 10, 10, 1) 2 1 [100.2]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.812 1.759 (1, 6, 10, 10) 1 1 [1.812]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.933 (1, 1, 10, 10, 3) 1 1 [0.961]
-Total_time - 102.972 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.1 96.907 (1, 6, 10, 10, 1) 2 1 [100.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.052 1.987 (1, 6, 10, 10) 1 1 [2.052]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.143 1.106 (1, 1, 10, 10, 3) 1 1 [1.143]
+Total_time - 103.295 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 851666d0cf..272ab21928 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,8 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
- 89%|########8 | 3.04M/3.42M [00:00<00:00, 31.7MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 33.5MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 88.0MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -565,7 +564,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.674 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.012 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 2ccc3828a3..ff315c7e37 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmppt6c9w_4/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp2w9e5ff8/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmppt6c9w_4/images/target contains 8144 images
-/tmp/tmppt6c9w_4/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp2w9e5ff8/images/target contains 8144 images
+/tmp/tmp2w9e5ff8/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2248 - accuracy: 0.9199 - val_loss: 0.1087 - val_accuracy: 0.9547 - 47s/epoch - 142ms/step
+328/328 - 46s - loss: 0.2100 - accuracy: 0.9274 - val_loss: 0.1252 - val_accuracy: 0.9581 - 46s/epoch - 140ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1000 - accuracy: 0.9631 - val_loss: 0.1361 - val_accuracy: 0.9551 - 43s/epoch - 131ms/step
+328/328 - 42s - loss: 0.1087 - accuracy: 0.9590 - val_loss: 0.1192 - val_accuracy: 0.9600 - 42s/epoch - 129ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0628 - accuracy: 0.9762 - val_loss: 0.0917 - val_accuracy: 0.9728 - 43s/epoch - 130ms/step
+328/328 - 42s - loss: 0.0666 - accuracy: 0.9762 - val_loss: 0.1455 - val_accuracy: 0.9509 - 42s/epoch - 129ms/step
-<keras.callbacks.History object at 0x7fa28c510750>
+<keras.callbacks.History object at 0x7fe076b89dd0>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 41.388 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 33.607 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 c92ac01c8a..6cbeaccbbe 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>06:42.910</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:37.533</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:41.388</p></td>
+<td><p>04:33.607</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:00.674</p></td>
+<td><p>01:02.012</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:48.544</p></td>
+<td><p>00:49.556</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.605</p></td>
+<td><p>00:08.514</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.696</p></td>
+<td><p>00:03.842</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
-<td><p>00:00.001</p></td>
+<td><p>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="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 291a7894f3..496ae3fa53 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>00:43.233</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.789</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>00:31.398</p></td>
+<td><p>00:32.863</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>00:10.239</p></td>
+<td><p>00:10.515</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>00:01.590</p></td>
+<td><p>00:01.404</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 beec8b8359..568381fb3e 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 0x7fa28c8103b0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fe0d6b7e5f0>
</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 ea8839c772..e3812906e3 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>00:07.156</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.084</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.772</p></td>
+<td><p>00:02.512</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>00:01.067</p></td>
+<td><p>00:01.154</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>00:00.561</p></td>
+<td><p>00:00.613</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>00:00.544</p></td>
+<td><p>00:00.593</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.112</p></td>
+<td><p>00:00.115</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -373,7 +373,7 @@
<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>00:00.032</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 e3b784ea37..9fd36da345 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/tmp6nukmr7s/input0.cc'\nsource_filename = \"/tmp/tmp6nukmr7s/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/tmp6zlnhnuw/input0.cc'\nsource_filename = \"/tmp/tmp6zlnhnuw/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 27cce8e675..3d36d9b28a 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 08ff39b782..a6fa0d37c1 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/f950b118a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 17bca7b46c..13b41511c0 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/f950b118a/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 713623f70c..91989442a2 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/f950b118a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 df7c644147..b6efcf445b 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/f950b118a/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 d57de7ad94..32860e1857 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/f950b118a/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 dbc8cdbdd9..318c5ba714 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/f950b118a/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 3b3c78b838..80cbc8ca55 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/f950b118a/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 fcc57e7f27..60a8e50da9 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/f950b118a/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 f5dc1622f6..59e83e3b83 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/f950b118a/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 9346a28409..1ee157400b 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/f950b118a/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 75d044ecc3..caba41b9d7 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/f950b118a/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 638e77e71f..c29acccefd 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/f950b118a/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 846c47d810..9465faae1b 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/f950b118a/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 3310950612..cdf80793a4 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/f950b118a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 0aa53af99f..f8dd1764cc 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/f950b118a/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 e230afb8a4..8105064ce3 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/f950b118a/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 a97054a105..4ff614c0c0 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/f950b118a/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 d2e68a8a08..0734a46657 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/f950b118a/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 ab1ff6abf9..40b0e9b9e4 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/f950b118a/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 184e651909..54b282ed52 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/f950b118a/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 00d5f7e91d..b3ef4e2e52 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/f950b118a/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 31481e9116..839554d72e 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/f950b118a/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 9df71973f4..3c564c5bde 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/f950b118a/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 4d2365069b..c2e2ddf330 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/f950b118a/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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/f950b118a/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/a15663654/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 99f87eb9d8..0e841201ca 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 dc3b78de7e..b96118361b 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>00:25.396</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:25.595</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>00:25.390</p></td>
+<td><p>00:25.589</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 5d74f59c38..91ac38b75c 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 28.07s!
+resnet18_v1 inference graph built in 28.14s!
</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 caa21193d4..8852fff2df 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 19.12s!
+yolov3-tiny inference graph built in 18.94s!
</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 b4d1cf5d27..bdffe5afdd 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>01:39.292</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:38.981</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>00:51.315</p></td>
+<td><p>00:51.069</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>00:47.977</p></td>
+<td><p>00:47.912</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 b5192ea640..e575d95dc6 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>00:03.107</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.199</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>00:02.665</p></td>
+<td><p>00:02.716</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>00:00.442</p></td>
+<td><p>00:00.483</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 c0f4b86653..1efc317eef 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>00:00.794</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.849</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>00:00.430</p></td>
+<td><p>00:00.441</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>00:00.364</p></td>
+<td><p>00:00.408</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 37767f867c..3c71fa7ff4 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,6 +491,10 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
+*E
+</pre></div>
+</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -578,7 +582,7 @@ 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: 94.808 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.889 ms
</pre></div>
</div>
</div>
@@ -642,6 +646,7 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
+*E
</pre></div>
</div>
</div>
@@ -652,7 +657,7 @@ 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 36.868 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 43.051 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 79fa9d6b6f..92cd8fcdf8 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: 1.12/1.12 result: MeasureResult(costs=(0.2400360736,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.9573395252227783, timestamp=1668131036.1820025) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
-No: 2 GFLOPS: 9.07/9.07 result: MeasureResult(costs=(0.029596561400000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7329578399658203, timestamp=1668131036.863362) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
-No: 3 GFLOPS: 10.23/10.23 result: MeasureResult(costs=(0.0262403184,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.634730339050293, timestamp=1668131038.2000988) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
-No: 4 GFLOPS: 3.92/10.23 result: MeasureResult(costs=(0.068548571,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2965543270111084, timestamp=1668131040.2106373) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
-No: 5 GFLOPS: 1.84/10.23 result: MeasureResult(costs=(0.14577125159999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.464296817779541, timestamp=1668131042.8572454) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 6 GFLOPS: 1.43/10.23 result: MeasureResult(costs=(0.1875068702,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.125948905944824, timestamp=1668131046.020351) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
-No: 7 GFLOPS: 14.31/14.31 result: MeasureResult(costs=(0.0187537442,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5044946670532227, timestamp=1668131047.2417636) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
-No: 8 GFLOPS: 11.65/14.31 result: MeasureResult(costs=(0.023041929200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5674543380737305, timestamp=1668131047.813514) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
-No: 9 GFLOPS: 3.27/14.31 result: MeasureResult(costs=(0.08202040660000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4349756240844727, timestamp=1668131049.4001324) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
-No: 10 GFLOPS: 10.53/14.31 result: MeasureResult(costs=(0.025494058799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5698449611663818, timestamp=1668131049.972506) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
+No: 1 GFLOPS: 0.89/0.89 result: MeasureResult(costs=(0.3007659048,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.955992698669434, timestamp=1668132616.9510393) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+No: 2 GFLOPS: 10.80/10.80 result: MeasureResult(costs=(0.0248455454,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5782978534698486, timestamp=1668132617.5614326) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+No: 3 GFLOPS: 12.39/12.39 result: MeasureResult(costs=(0.0216652868,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.48595094680786133, timestamp=1668132618.8351378) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
+No: 4 GFLOPS: 13.14/13.14 result: MeasureResult(costs=(0.0204259016,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4742145538330078, timestamp=1668132620.0899937) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+No: 5 GFLOPS: 1.72/13.14 result: MeasureResult(costs=(0.1560466606,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.606656789779663, timestamp=1668132622.8635302) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 6 GFLOPS: 0.95/13.14 result: MeasureResult(costs=(0.2838922176,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.699040412902832, timestamp=1668132628.3293188) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
+No: 7 GFLOPS: 10.82/13.14 result: MeasureResult(costs=(0.024816031199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5873422622680664, timestamp=1668132628.8960543) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+No: 8 GFLOPS: 1.22/13.14 result: MeasureResult(costs=(0.2194521924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.6838390827178955, timestamp=1668132632.6119697) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+No: 9 GFLOPS: 10.90/13.14 result: MeasureResult(costs=(0.0246296524,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5192666053771973, timestamp=1668132633.2504795) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
+No: 10 GFLOPS: 1.58/13.14 result: MeasureResult(costs=(0.1694415808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.830249309539795, timestamp=1668132636.127075) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
</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 9c6066232d..628d9f63a8 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 513.8065643800019, 'median': 513.9278934999766, 'std': 1.6299110458413983}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 514.875446879978, 'median': 515.1379385999917, 'std': 1.4243465931917811}
</pre></div>
</div>
</div>
@@ -712,178 +712,177 @@ 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: 23.56/ 23.56 GFLOPS | Progress: (4/20) | 8.20 s
-[Task 1/25] Current/Best: 17.80/ 23.56 GFLOPS | Progress: (8/20) | 12.71 s
-[Task 1/25] Current/Best: 15.20/ 23.56 GFLOPS | Progress: (12/20) | 14.64 s
-[Task 1/25] Current/Best: 17.53/ 23.56 GFLOPS | Progress: (16/20) | 16.59 s
-[Task 1/25] Current/Best: 9.70/ 23.56 GFLOPS | Progress: (20/20) | 20.07 s Done.
+[Task 1/25] Current/Best: 12.16/ 16.54 GFLOPS | Progress: (4/20) | 6.71 s
+[Task 1/25] Current/Best: 6.76/ 16.54 GFLOPS | Progress: (8/20) | 10.48 s
+[Task 1/25] Current/Best: 9.72/ 23.02 GFLOPS | Progress: (12/20) | 14.04 s
+[Task 1/25] Current/Best: 15.85/ 23.02 GFLOPS | Progress: (16/20) | 16.53 s
+[Task 1/25] Current/Best: 18.93/ 23.02 GFLOPS | Progress: (20/20) | 18.74 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 6.14/ 20.75 GFLOPS | Progress: (4/20) | 2.52 s
-[Task 2/25] Current/Best: 19.08/ 20.75 GFLOPS | Progress: (8/20) | 3.87 s
-[Task 2/25] Current/Best: 9.90/ 20.75 GFLOPS | Progress: (12/20) | 5.45 s
-[Task 2/25] Current/Best: 6.00/ 20.75 GFLOPS | Progress: (16/20) | 6.87 s
-[Task 2/25] Current/Best: 12.18/ 20.75 GFLOPS | Progress: (20/20) | 8.63 s Done.
+[Task 2/25] Current/Best: 9.62/ 17.29 GFLOPS | Progress: (4/20) | 2.78 s
+[Task 2/25] Current/Best: 13.01/ 17.29 GFLOPS | Progress: (8/20) | 3.96 s
+[Task 2/25] Current/Best: 10.80/ 18.27 GFLOPS | Progress: (12/20) | 5.01 s
+[Task 2/25] Current/Best: 16.05/ 18.27 GFLOPS | Progress: (16/20) | 6.65 s
+[Task 2/25] Current/Best: 14.35/ 18.27 GFLOPS | Progress: (20/20) | 7.95 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 11.99/ 11.99 GFLOPS | Progress: (4/20) | 4.04 s
-[Task 3/25] Current/Best: 15.74/ 21.45 GFLOPS | Progress: (8/20) | 5.68 s
-[Task 3/25] Current/Best: 3.17/ 21.45 GFLOPS | Progress: (12/20) | 8.37 s
-[Task 3/25] Current/Best: 9.86/ 21.45 GFLOPS | Progress: (16/20) | 10.80 s
-[Task 3/25] Current/Best: 13.55/ 21.45 GFLOPS | Progress: (20/20) | 12.77 s Done.
+[Task 3/25] Current/Best: 5.79/ 14.43 GFLOPS | Progress: (4/20) | 3.87 s
+[Task 3/25] Current/Best: 10.32/ 17.22 GFLOPS | Progress: (8/20) | 5.91 s
+[Task 3/25] Current/Best: 8.08/ 22.24 GFLOPS | Progress: (12/20) | 7.85 s
+[Task 3/25] Current/Best: 9.96/ 22.24 GFLOPS | Progress: (16/20) | 10.34 s
+[Task 3/25] Current/Best: 7.39/ 22.24 GFLOPS | Progress: (20/20) | 12.51 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 11.32/ 21.55 GFLOPS | Progress: (4/20) | 3.90 s
-[Task 4/25] Current/Best: 8.01/ 22.97 GFLOPS | Progress: (8/20) | 5.98 s
-[Task 4/25] Current/Best: 6.20/ 22.97 GFLOPS | Progress: (12/20) | 7.89 s
-[Task 4/25] Current/Best: 2.28/ 22.97 GFLOPS | Progress: (16/20) | 9.61 s
-[Task 4/25] Current/Best: 11.70/ 22.97 GFLOPS | Progress: (20/20) | 12.50 s Done.
+[Task 4/25] Current/Best: 5.17/ 8.53 GFLOPS | Progress: (4/20) | 6.42 s
+[Task 4/25] Current/Best: 3.98/ 11.33 GFLOPS | Progress: (8/20) | 15.08 s
+[Task 4/25] Current/Best: 12.45/ 12.45 GFLOPS | Progress: (12/20) | 26.43 s
+[Task 4/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (16/20) | 29.09 s
+[Task 4/25] Current/Best: 15.62/ 19.95 GFLOPS | Progress: (20/20) | 34.21 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 5.61/ 18.16 GFLOPS | Progress: (4/20) | 3.50 s
-[Task 5/25] Current/Best: 6.17/ 18.16 GFLOPS | Progress: (8/20) | 5.70 s
-[Task 5/25] Current/Best: 12.76/ 18.16 GFLOPS | Progress: (12/20) | 7.72 s
-[Task 5/25] Current/Best: 16.19/ 18.16 GFLOPS | Progress: (16/20) | 9.54 s
-[Task 5/25] Current/Best: 16.15/ 18.16 GFLOPS | Progress: (20/20) | 11.31 s Done.
+[Task 5/25] Current/Best: 11.42/ 17.88 GFLOPS | Progress: (4/20) | 3.25 s
+[Task 5/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (8/20) | 4.80 s
+[Task 5/25] Current/Best: 9.13/ 20.72 GFLOPS | Progress: (12/20) | 6.59 s
+[Task 5/25] Current/Best: 19.09/ 20.72 GFLOPS | Progress: (16/20) | 8.24 s
+[Task 5/25] Current/Best: 13.56/ 22.95 GFLOPS | Progress: (20/20) | 10.33 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 13.95/ 17.78 GFLOPS | Progress: (4/20) | 4.78 s
-[Task 6/25] Current/Best: 10.09/ 17.78 GFLOPS | Progress: (8/20) | 6.98 s
-[Task 6/25] Current/Best: 5.54/ 17.78 GFLOPS | Progress: (12/20) | 10.12 s
-[Task 6/25] Current/Best: 14.06/ 17.78 GFLOPS | Progress: (16/20) | 13.13 s
-[Task 6/25] Current/Best: 14.70/ 17.78 GFLOPS | Progress: (20/20) | 16.05 s Done.
+[Task 6/25] Current/Best: 15.33/ 15.33 GFLOPS | Progress: (4/20) | 5.19 s
+[Task 6/25] Current/Best: 12.54/ 18.63 GFLOPS | Progress: (8/20) | 7.51 s
+[Task 6/25] Current/Best: 14.42/ 18.63 GFLOPS | Progress: (12/20) | 10.46 s
+[Task 6/25] Current/Best: 13.82/ 18.63 GFLOPS | Progress: (16/20) | 12.35 s
+[Task 6/25] Current/Best: 11.40/ 18.63 GFLOPS | Progress: (20/20) | 17.84 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 3.14/ 18.40 GFLOPS | Progress: (4/20) | 3.76 s
-[Task 7/25] Current/Best: 15.23/ 19.39 GFLOPS | Progress: (8/20) | 6.18 s
-[Task 7/25] Current/Best: 6.82/ 19.39 GFLOPS | Progress: (12/20) | 8.27 s
-[Task 7/25] Current/Best: 18.40/ 19.39 GFLOPS | Progress: (16/20) | 10.36 s
-[Task 7/25] Current/Best: 5.46/ 22.40 GFLOPS | Progress: (20/20) | 12.45 s Done.
+[Task 7/25] Current/Best: 14.09/ 14.09 GFLOPS | Progress: (4/20) | 3.66 s
+[Task 7/25] Current/Best: 19.49/ 19.49 GFLOPS | Progress: (8/20) | 5.42 s
+[Task 7/25] Current/Best: 11.42/ 20.28 GFLOPS | Progress: (12/20) | 8.14 s
+[Task 7/25] Current/Best: 11.77/ 20.28 GFLOPS | Progress: (16/20) | 10.41 s
+[Task 7/25] Current/Best: 22.44/ 22.44 GFLOPS | Progress: (20/20) | 12.13 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 8.91/ 12.58 GFLOPS | Progress: (4/20) | 7.42 s
-[Task 8/25] Current/Best: 12.75/ 12.75 GFLOPS | Progress: (8/20) | 11.96 s
-[Task 8/25] Current/Best: 5.56/ 15.61 GFLOPS | Progress: (12/20) | 15.09 s
-[Task 8/25] Current/Best: 3.50/ 15.78 GFLOPS | Progress: (16/20) | 17.79 s
-[Task 8/25] Current/Best: 9.73/ 15.78 GFLOPS | Progress: (20/20) | 25.47 s Done.
+[Task 8/25] Current/Best: 13.23/ 13.23 GFLOPS | Progress: (4/20) | 4.69 s
+[Task 8/25] Current/Best: 13.52/ 13.52 GFLOPS | Progress: (8/20) | 11.51 s
+[Task 8/25] Current/Best: 4.55/ 14.06 GFLOPS | Progress: (12/20) | 15.09 s
+[Task 8/25] Current/Best: 6.52/ 18.50 GFLOPS | Progress: (16/20) | 18.11 s
+[Task 8/25] Current/Best: 17.36/ 18.50 GFLOPS | Progress: (20/20) | 20.30 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 8.45/ 12.36 GFLOPS | Progress: (4/20) | 5.44 s
-[Task 9/25] Current/Best: 8.90/ 12.36 GFLOPS | Progress: (8/20) | 7.65 s
-[Task 9/25] Current/Best: 6.56/ 20.30 GFLOPS | Progress: (12/20) | 9.16 s
-[Task 9/25] Current/Best: 17.04/ 21.09 GFLOPS | Progress: (16/20) | 11.58 s
-[Task 9/25] Current/Best: 6.86/ 21.09 GFLOPS | Progress: (20/20) | 16.57 s Done.
-
+[Task 9/25] Current/Best: 9.98/ 19.87 GFLOPS | Progress: (4/20) | 5.29 s
+[Task 9/25] Current/Best: 9.25/ 19.87 GFLOPS | Progress: (8/20) | 10.82 s
+[Task 9/25] Current/Best: 12.58/ 19.87 GFLOPS | Progress: (12/20) | 21.66 s
+[Task 9/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (16/20) | 32.53 s
+[Task 9/25] Current/Best: 12.71/ 19.95 GFLOPS | Progress: (20/20) | 39.64 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.02/ 22.21 GFLOPS | Progress: (4/20) | 2.73 s
-[Task 10/25] Current/Best: 5.43/ 22.21 GFLOPS | Progress: (8/20) | 4.28 s
-[Task 10/25] Current/Best: 10.01/ 22.21 GFLOPS | Progress: (12/20) | 5.81 s
-[Task 10/25] Current/Best: 13.95/ 22.21 GFLOPS | Progress: (16/20) | 7.36 s
-[Task 10/25] Current/Best: 1.59/ 22.21 GFLOPS | Progress: (20/20) | 9.34 s Done.
+[Task 10/25] Current/Best: 10.68/ 12.27 GFLOPS | Progress: (4/20) | 4.83 s
+[Task 10/25] Current/Best: 8.59/ 20.55 GFLOPS | Progress: (8/20) | 6.58 s
+[Task 10/25] Current/Best: 9.97/ 20.55 GFLOPS | Progress: (12/20) | 8.38 s
+[Task 10/25] Current/Best: 16.27/ 20.55 GFLOPS | Progress: (16/20) | 10.06 s
+[Task 10/25] Current/Best: 5.47/ 20.61 GFLOPS | Progress: (20/20) | 11.48 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 18.62/ 18.62 GFLOPS | Progress: (4/20) | 3.06 s
-[Task 11/25] Current/Best: 14.35/ 22.59 GFLOPS | Progress: (8/20) | 4.93 s
-[Task 11/25] Current/Best: 11.32/ 22.59 GFLOPS | Progress: (12/20) | 7.59 s
-[Task 11/25] Current/Best: 21.23/ 22.59 GFLOPS | Progress: (16/20) | 9.50 s
-[Task 11/25] Current/Best: 9.90/ 22.59 GFLOPS | Progress: (20/20) | 11.64 s Done.
+[Task 11/25] Current/Best: 21.33/ 21.33 GFLOPS | Progress: (4/20) | 3.88 s
+[Task 11/25] Current/Best: 5.06/ 21.33 GFLOPS | Progress: (8/20) | 6.18 s
+[Task 11/25] Current/Best: 23.05/ 23.05 GFLOPS | Progress: (12/20) | 8.08 s
+[Task 11/25] Current/Best: 12.28/ 23.05 GFLOPS | Progress: (16/20) | 10.67 s
+[Task 11/25] Current/Best: 12.46/ 23.05 GFLOPS | Progress: (20/20) | 12.86 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 1.58/ 15.73 GFLOPS | Progress: (4/20) | 7.13 s
-[Task 12/25] Current/Best: 13.49/ 21.09 GFLOPS | Progress: (8/20) | 10.57 s
-[Task 12/25] Current/Best: 13.01/ 21.09 GFLOPS | Progress: (12/20) | 18.78 s
-[Task 12/25] Current/Best: 9.75/ 21.09 GFLOPS | Progress: (16/20) | 22.68 s
-[Task 12/25] Current/Best: 21.04/ 21.09 GFLOPS | Progress: (20/20) | 25.74 s Done.
+[Task 12/25] Current/Best: 11.50/ 11.50 GFLOPS | Progress: (4/20) | 6.20 s
+[Task 12/25] Current/Best: 15.55/ 15.55 GFLOPS | Progress: (8/20) | 12.29 s
+[Task 12/25] Current/Best: 18.45/ 18.45 GFLOPS | Progress: (12/20) | 14.65 s
+[Task 12/25] Current/Best: 7.00/ 18.45 GFLOPS | Progress: (16/20) | 18.25 s
+[Task 12/25] Current/Best: 15.14/ 18.45 GFLOPS | Progress: (20/20) | 21.18 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 12.67/ 18.71 GFLOPS | Progress: (4/20) | 4.63 s
-[Task 13/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (8/20) | 7.69 s
-[Task 13/25] Current/Best: 17.06/ 21.36 GFLOPS | Progress: (12/20) | 11.16 s
-[Task 13/25] Current/Best: 17.28/ 21.36 GFLOPS | Progress: (16/20) | 14.34 s
-[Task 13/25] Current/Best: 18.82/ 21.36 GFLOPS | Progress: (20/20) | 16.41 s Done.
+[Task 13/25] Current/Best: 5.77/ 17.33 GFLOPS | Progress: (4/20) | 4.17 s
+[Task 13/25] Current/Best: 16.83/ 19.98 GFLOPS | Progress: (8/20) | 7.84 s
+[Task 13/25] Current/Best: 15.96/ 19.98 GFLOPS | Progress: (12/20) | 10.32 s
+[Task 13/25] Current/Best: 16.87/ 22.40 GFLOPS | Progress: (16/20) | 13.63 s
+[Task 13/25] Current/Best: 11.94/ 22.40 GFLOPS | Progress: (20/20) | 16.14 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.12/ 21.18 GFLOPS | Progress: (4/20) | 3.39 s
-[Task 14/25] Current/Best: 15.44/ 21.18 GFLOPS | Progress: (8/20) | 5.17 s
-[Task 14/25] Current/Best: 17.47/ 21.18 GFLOPS | Progress: (12/20) | 9.33 s
-[Task 14/25] Current/Best: 12.19/ 21.18 GFLOPS | Progress: (16/20) | 11.32 s
-[Task 14/25] Current/Best: 18.83/ 21.18 GFLOPS | Progress: (20/20) | 14.87 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 13.93/ 13.93 GFLOPS | Progress: (4/20) | 5.06 s
-[Task 15/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (8/20) | 8.73 s
-[Task 15/25] Current/Best: 9.29/ 19.69 GFLOPS | Progress: (12/20) | 9.90 s Done.
+[Task 14/25] Current/Best: 13.23/ 15.57 GFLOPS | Progress: (4/20) | 5.30 s
+[Task 14/25] Current/Best: 10.98/ 15.57 GFLOPS | Progress: (8/20) | 10.12 s
+[Task 14/25] Current/Best: 13.30/ 15.57 GFLOPS | Progress: (12/20) | 12.56 s
+[Task 14/25] Current/Best: 8.43/ 16.54 GFLOPS | Progress: (16/20) | 17.84 s Done.
-[Task 15/25] Current/Best: 19.66/ 19.69 GFLOPS | Progress: (16/20) | 11.23 s
-[Task 15/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (20/20) | 12.45 s Done.
+[Task 14/25] Current/Best: 15.22/ 16.54 GFLOPS | Progress: (20/20) | 20.98 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 15/25] Current/Best: 13.15/ 16.63 GFLOPS | Progress: (4/20) | 4.14 s
+[Task 15/25] Current/Best: 8.77/ 18.17 GFLOPS | Progress: (8/20) | 5.57 s
+[Task 15/25] Current/Best: 11.76/ 18.17 GFLOPS | Progress: (12/20) | 7.03 s
+[Task 15/25] Current/Best: 5.16/ 18.17 GFLOPS | Progress: (16/20) | 13.37 s
+[Task 15/25] Current/Best: 9.93/ 18.27 GFLOPS | Progress: (20/20) | 14.66 s Done.
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 10.28/ 17.61 GFLOPS | Progress: (4/20) | 3.96 s
-[Task 16/25] Current/Best: 5.87/ 20.29 GFLOPS | Progress: (8/20) | 5.29 s
-[Task 16/25] Current/Best: 15.80/ 20.29 GFLOPS | Progress: (12/20) | 6.89 s
-[Task 16/25] Current/Best: 13.77/ 20.29 GFLOPS | Progress: (16/20) | 8.66 s
-[Task 16/25] Current/Best: 14.99/ 20.29 GFLOPS | Progress: (20/20) | 10.21 s Done.
+[Task 16/25] Current/Best: 17.18/ 19.29 GFLOPS | Progress: (4/20) | 3.30 s
+[Task 16/25] Current/Best: 6.16/ 19.29 GFLOPS | Progress: (8/20) | 6.90 s
+[Task 16/25] Current/Best: 21.48/ 21.48 GFLOPS | Progress: (12/20) | 8.15 s
+[Task 16/25] Current/Best: 7.48/ 21.48 GFLOPS | Progress: (16/20) | 11.33 s
+[Task 16/25] Current/Best: 14.15/ 21.48 GFLOPS | Progress: (20/20) | 14.36 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 15.48/ 21.80 GFLOPS | Progress: (4/20) | 3.37 s
-[Task 17/25] Current/Best: 12.25/ 21.80 GFLOPS | Progress: (8/20) | 5.24 s
-[Task 17/25] Current/Best: 17.77/ 21.80 GFLOPS | Progress: (12/20) | 7.51 s
-[Task 17/25] Current/Best: 7.65/ 21.80 GFLOPS | Progress: (16/20) | 10.21 s
-[Task 17/25] Current/Best: 9.95/ 21.80 GFLOPS | Progress: (20/20) | 12.54 s Done.
+[Task 17/25] Current/Best: 14.49/ 23.50 GFLOPS | Progress: (4/20) | 3.45 s
+[Task 17/25] Current/Best: 21.38/ 23.50 GFLOPS | Progress: (8/20) | 5.70 s
+[Task 17/25] Current/Best: 18.95/ 23.50 GFLOPS | Progress: (12/20) | 7.59 s
+[Task 17/25] Current/Best: 11.17/ 23.50 GFLOPS | Progress: (16/20) | 10.91 s
+[Task 17/25] Current/Best: 3.09/ 23.50 GFLOPS | Progress: (20/20) | 13.80 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 13.46/ 16.11 GFLOPS | Progress: (4/20) | 3.45 s
-[Task 18/25] Current/Best: 6.52/ 18.10 GFLOPS | Progress: (8/20) | 5.36 s
-[Task 18/25] Current/Best: 13.83/ 18.10 GFLOPS | Progress: (12/20) | 9.70 s
-[Task 18/25] Current/Best: 3.04/ 20.16 GFLOPS | Progress: (16/20) | 12.38 s
-[Task 18/25] Current/Best: 13.67/ 20.16 GFLOPS | Progress: (20/20) | 15.65 s Done.
+[Task 18/25] Current/Best: 10.89/ 12.18 GFLOPS | Progress: (4/20) | 4.21 s
+[Task 18/25] Current/Best: 4.76/ 22.28 GFLOPS | Progress: (8/20) | 6.97 s
+[Task 18/25] Current/Best: 5.91/ 22.28 GFLOPS | Progress: (12/20) | 10.55 s
+[Task 18/25] Current/Best: 11.91/ 22.28 GFLOPS | Progress: (16/20) | 13.43 s
+[Task 18/25] Current/Best: 17.53/ 22.28 GFLOPS | Progress: (20/20) | 19.59 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 10.78/ 20.90 GFLOPS | Progress: (4/20) | 4.43 s
-[Task 19/25] Current/Best: 17.06/ 20.90 GFLOPS | Progress: (8/20) | 9.08 s
-[Task 19/25] Current/Best: 12.62/ 20.90 GFLOPS | Progress: (12/20) | 12.41 s
-[Task 19/25] Current/Best: 16.05/ 20.90 GFLOPS | Progress: (16/20) | 15.80 s
-[Task 19/25] Current/Best: 3.08/ 20.90 GFLOPS | Progress: (20/20) | 20.03 s Done.
+[Task 19/25] Current/Best: 9.97/ 22.56 GFLOPS | Progress: (4/20) | 5.57 s
+[Task 19/25] Current/Best: 7.81/ 22.56 GFLOPS | Progress: (8/20) | 8.15 s
+[Task 19/25] Current/Best: 10.83/ 22.56 GFLOPS | Progress: (12/20) | 11.33 s
+[Task 19/25] Current/Best: 10.98/ 22.56 GFLOPS | Progress: (16/20) | 15.19 s
+[Task 19/25] Current/Best: 2.70/ 22.56 GFLOPS | Progress: (20/20) | 19.04 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 14.81/ 17.50 GFLOPS | Progress: (4/20) | 3.28 s
-[Task 20/25] Current/Best: 9.32/ 17.50 GFLOPS | Progress: (8/20) | 5.42 s
-[Task 20/25] Current/Best: 10.26/ 17.50 GFLOPS | Progress: (12/20) | 8.56 s
-[Task 20/25] Current/Best: 15.18/ 17.50 GFLOPS | Progress: (16/20) | 10.55 s
-[Task 20/25] Current/Best: 6.18/ 17.50 GFLOPS | Progress: (20/20) | 14.05 s
+[Task 20/25] Current/Best: 14.00/ 18.18 GFLOPS | Progress: (4/20) | 3.41 s
+[Task 20/25] Current/Best: 7.46/ 18.18 GFLOPS | Progress: (8/20) | 7.16 s
+[Task 20/25] Current/Best: 6.57/ 18.18 GFLOPS | Progress: (12/20) | 9.30 s
+[Task 20/25] Current/Best: 16.41/ 18.18 GFLOPS | Progress: (16/20) | 13.14 s
+[Task 20/25] Current/Best: 9.12/ 18.18 GFLOPS | Progress: (20/20) | 16.04 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 10.67/ 10.67 GFLOPS | Progress: (4/20) | 3.45 s Done.
+[Task 21/25] Current/Best: 5.05/ 23.10 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 21/25] Current/Best: 4.73/ 23.10 GFLOPS | Progress: (8/20) | 5.58 s
+[Task 21/25] Current/Best: 14.92/ 23.10 GFLOPS | Progress: (12/20) | 7.79 s
+[Task 21/25] Current/Best: 10.24/ 23.10 GFLOPS | Progress: (16/20) | 11.74 s Done.
-[Task 21/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (8/20) | 5.53 s
-[Task 21/25] Current/Best: 8.04/ 18.81 GFLOPS | Progress: (12/20) | 7.48 s
-[Task 21/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (16/20) | 9.14 s
-[Task 21/25] Current/Best: 17.75/ 19.24 GFLOPS | Progress: (20/20) | 11.52 s
+[Task 21/25] Current/Best: 11.98/ 23.10 GFLOPS | Progress: (20/20) | 13.66 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 7.96/ 14.11 GFLOPS | Progress: (4/20) | 5.49 s
-[Task 22/25] Current/Best: 20.39/ 20.39 GFLOPS | Progress: (8/20) | 6.94 s
-[Task 22/25] Current/Best: 7.65/ 20.39 GFLOPS | Progress: (12/20) | 9.17 s
-[Task 22/25] Current/Best: 17.60/ 20.39 GFLOPS | Progress: (16/20) | 11.89 s
-[Task 22/25] Current/Best: 16.22/ 20.39 GFLOPS | Progress: (20/20) | 16.59 s Done.
+[Task 22/25] Current/Best: 12.21/ 15.35 GFLOPS | Progress: (4/20) | 3.79 s
+[Task 22/25] Current/Best: 9.81/ 18.69 GFLOPS | Progress: (8/20) | 6.97 s
+[Task 22/25] Current/Best: 6.16/ 18.69 GFLOPS | Progress: (12/20) | 8.40 s
+[Task 22/25] Current/Best: 8.90/ 19.81 GFLOPS | Progress: (16/20) | 10.29 s
+[Task 22/25] Current/Best: 7.16/ 20.11 GFLOPS | Progress: (20/20) | 11.92 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 8.01/ 19.48 GFLOPS | Progress: (4/20) | 4.25 s
-[Task 23/25] Current/Best: 18.84/ 19.48 GFLOPS | Progress: (8/20) | 6.69 s
-[Task 23/25] Current/Best: 19.88/ 19.88 GFLOPS | Progress: (12/20) | 8.71 s
-[Task 23/25] Current/Best: 17.15/ 19.88 GFLOPS | Progress: (16/20) | 12.90 s
-[Task 23/25] Current/Best: 19.48/ 19.88 GFLOPS | Progress: (20/20) | 15.59 s Done.
+[Task 23/25] Current/Best: 21.14/ 22.60 GFLOPS | Progress: (4/20) | 6.46 s
+[Task 23/25] Current/Best: 19.49/ 22.60 GFLOPS | Progress: (8/20) | 10.31 s
+[Task 23/25] Current/Best: 9.86/ 22.60 GFLOPS | Progress: (12/20) | 13.26 s
+[Task 23/25] Current/Best: 6.14/ 22.60 GFLOPS | Progress: (16/20) | 15.59 s
+[Task 23/25] Current/Best: 10.79/ 22.60 GFLOPS | Progress: (20/20) | 17.67 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 9.55/ 9.55 GFLOPS | Progress: (4/20) | 12.24 s
-[Task 24/25] Current/Best: 7.52/ 9.55 GFLOPS | Progress: (8/20) | 23.51 s
-[Task 24/25] Current/Best: 3.47/ 9.55 GFLOPS | Progress: (12/20) | 25.65 s
-[Task 24/25] Current/Best: 3.21/ 9.55 GFLOPS | Progress: (16/20) | 36.39 s
-[Task 24/25] Current/Best: 3.61/ 9.55 GFLOPS | Progress: (20/20) | 39.63 s Done.
-
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 7.58/ 7.58 GFLOPS | Progress: (4/20) | 12.25 s
-[Task 25/25] Current/Best: 8.21/ 8.56 GFLOPS | Progress: (8/20) | 22.38 s
-[Task 25/25] Current/Best: 3.46/ 8.56 GFLOPS | Progress: (12/20) | 23.55 s
-[Task 25/25] Current/Best: 1.55/ 8.56 GFLOPS | Progress: (16/20) | 30.83 s
-[Task 25/25] Current/Best: 7.54/ 8.56 GFLOPS | Progress: (20/20) | 41.56 s
+[Task 24/25] Current/Best: 3.86/ 8.79 GFLOPS | Progress: (4/20) | 2.86 s
+[Task 24/25] Current/Best: 0.58/ 8.79 GFLOPS | Progress: (8/20) | 6.13 s
+[Task 24/25] Current/Best: 3.81/ 8.79 GFLOPS | Progress: (12/20) | 16.87 s
+[Task 24/25] Current/Best: 3.49/ 10.45 GFLOPS | Progress: (16/20) | 27.34 s
+[Task 24/25] Current/Best: 7.03/ 10.45 GFLOPS | Progress: (20/20) | 34.09 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 25/25] Current/Best: 3.46/ 9.69 GFLOPS | Progress: (4/20) | 4.66 s
+[Task 25/25] Current/Best: 6.06/ 9.69 GFLOPS | Progress: (8/20) | 11.14 s
+[Task 25/25] Current/Best: 6.91/ 9.69 GFLOPS | Progress: (12/20) | 21.89 s
+[Task 25/25] Current/Best: 3.51/ 9.69 GFLOPS | Progress: (16/20) | 32.62 s
+[Task 25/25] Current/Best: 5.78/ 9.69 GFLOPS | Progress: (20/20) | 43.32 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -944,8 +943,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621105
-class='n02123159 tiger cat' with probability=0.356377
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621102
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -982,8 +981,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 417.815636309997, 'median': 417.1192714999961, 'std': 4.3123419468717845}
-unoptimized: {'mean': 513.8065643800019, 'median': 513.9278934999766, 'std': 1.6299110458413983}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 401.1140108500149, 'median': 399.01219244998174, 'std': 4.410206059196968}
+unoptimized: {'mean': 514.875446879978, 'median': 515.1379385999917, 'std': 1.4243465931917811}
</pre></div>
</div>
</div>
@@ -997,7 +996,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 32.481 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 21.271 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 08ad52c641..88add08b08 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>1.265e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>2.242e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 3066908284..90a3e54263 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, 0x1294ce60)), stage(b, placeholder(b, 0x15ece6f0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x9d3de00)), stage(b, placeholder(b, 0x23defe70)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 4a18d8fd29..ccd20fa31b 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>14:10.266</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:11.349</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>10:32.481</p></td>
+<td><p>11:21.271</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>01:36.868</p></td>
+<td><p>01:43.051</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.493</p></td>
+<td><p>01:00.781</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>00:36.249</p></td>
+<td><p>00:36.328</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>00:21.692</p></td>
+<td><p>00:28.083</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.772</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.841</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.541</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.776</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>00:00.163</p></td>
+<td><p>00:00.208</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
@@ -385,18 +385,18 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.001</p></td>
+<td><p>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="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>
-<tr class="row-even"><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-even"><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>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index f837bfa5af..636d661aa8 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -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 7.87341999966884e-06 1.0
- naive 6.7052e-06 0.8516248339707553
-parallel 6.9386e-06 0.8812688768402855
- vector 2.4577299999999996e-05 3.12155327685221
+ numpy 7.782479997331393e-06 1.0
+ naive 7.4378e-06 0.955710776327137
+parallel 6.954899999999999e-06 0.8936611468818204
+ vector 2.4541199999999998e-05 3.153390694022363
</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: 0.018552
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019019
</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: 3.438324
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.381993
</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: 0.302397
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.302984
</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: 0.340223
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.342094
@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: 0.115306
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.118003
@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: 0.107714
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108422
@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: 0.110911
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110895
@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: 0.146020
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146388
@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 3.4383240071000003 1.0
- blocking 0.3023969382 0.08794893604429442
- vectorization 0.3402233243 0.09895033847812265
-loop permutation 0.11530623439999999 0.03353559296968443
- array packing 0.10771403859999999 0.03132748349997698
- block caching 0.11091117549999999 0.0322573367928598
- parallelization 0.14601966859999999 0.042468268929418886
+ none 3.3819934623999997 1.0
+ blocking 0.3029840328 0.08958740936920388
+ vectorization 0.34209401229999997 0.10115158887895549
+loop permutation 0.1180031295 0.0348915900671967
+ array packing 0.10842177719999999 0.03205854133232401
+ block caching 0.1108952911 0.03278991882536172
+ parallelization 0.1463876009 0.04328441273689436
</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 1.493 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.781 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>