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 2022/11/08 19:30:23 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@be30238947305ccbf63655fb11162e726c319804)
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 692ab8fb33 deploying docs (apache/tvm@be30238947305ccbf63655fb11162e726c319804)
692ab8fb33 is described below
commit 692ab8fb33a831f9f9b03c527280273fcb1a9706
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Nov 8 19:30:16 2022 +0000
deploying docs (apache/tvm@be30238947305ccbf63655fb11162e726c319804)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 293847 -> 314727 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22348 -> 23008 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 | 4 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1498 ++++++++++----------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 301 ++--
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 213 ++-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 13 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 57 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 46 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 7 +-
docs/how_to/compile_models/from_pytorch.html | 8 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 36 +-
docs/how_to/deploy_models/deploy_prequantized.html | 4 +-
.../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 | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1498 ++++++++++----------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 301 ++--
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 213 ++-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
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 | 8 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 271 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 46 +-
126 files changed, 2808 insertions(+), 2809 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 71e241b4ac..44d42e7073 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 20e0aa607a..979e8de9bd 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 a7c233c60b..5c612121d1 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 9.144 seconds)
+ **Total running time of the script:** ( 1 minutes 6.989 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 112869d658..f07f69707a 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 963ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 971ms/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 9e78abba64..3d60239234 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.zipac2632f8-a4b0-46fa-ba95-f4230d4f741c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip3a337837-a906-4c42-9ccc-15983d4ed30b 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 2dc07bdc74..9c5c8031f9 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]
25%|##4 | 10.3M/41.5M [00:00<00:00, 107MB/s]
49%|####9 | 20.5M/41.5M [00:00<00:00, 107MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 109MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 121MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
30%|##9 | 12.3M/41.5M [00:00<00:00, 129MB/s]
59%|#####9 | 24.6M/41.5M [00:00<00:00, 78.5MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 107MB/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 b74939bec3..984986d953 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
31%|### | 13.7M/44.7M [00:00<00:00, 144MB/s]
61%|######1 | 27.5M/44.7M [00:00<00:00, 115MB/s]
87%|########6 | 38.7M/44.7M [00:00<00:00, 108MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 110MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
28%|##7 | 12.3M/44.7M [00:00<00:00, 129MB/s]
55%|#####5 | 24.6M/44.7M [00:00<00:00, 110MB/s]
79%|#######8 | 35.2M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 107MB/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 175746710d..f7f56cc1a8 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 11.266 seconds)
+ **Total running time of the script:** ( 1 minutes 10.697 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 7846fa675b..e440443ff2 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
=================
-**05:42.569** total execution time for **how_to_compile_models** files:
+**05:40.740** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.266 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.697 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.144 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:06.989 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.834 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.623 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.174 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.963 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.563 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.778 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.227 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.027 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.467 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.651 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.754 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.905 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.777 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.726 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.363 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.382 | 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 7b46aaf74d..db49265ef1 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)
- 17.3620 16.1833 23.2615 15.7846 2.2554
+ 16.4628 16.6644 17.0116 15.8147 0.4126
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 6ec2edd239..13a1623c67 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]
7%|6 | 11.9M/170M [00:00<00:01, 125MB/s]
14%|#3 | 23.8M/170M [00:00<00:01, 109MB/s]
20%|## | 34.3M/170M [00:00<00:01, 105MB/s]
26%|##6 | 44.3M/170M [00:00<00:01, 103MB/s]
32%|###1 | 54.2M/170M [00:00<00:01, 102MB/s]
38%|###7 | 63.9M/170M [00:00<00:01, 101MB/s]
43%|####3 | 73.6M/170M [00:00<00:01, 101MB/s]
49%|####9 | 83.2M/170M [00:00<00:00, 101MB/s]
55%|#####4 | 92.9M/170M [00:00<00:00, 100MB/s]
60%|###### | 102M/170M [00:01<00:00, 100MB/s]
66%|######5 | 112M/170M [00:01<00:00, 98.6MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 101MB/s]
78%|#######7 | 132M/170M [00:01<00:00, 101MB/s]
83%|########3 | 141M/170M [00:01<00:00, 100MB/s]
89%|########8 | 151M/170M [00:01<00:00, 100MB/s]
94%|#########4| 160M/170M [00:01<00:00, 99.4MB/s]
100%|##########| 170M/170M [00:01<00:00, 101MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
8%|7 | 12.8M/170M [00:00<00:01, 134MB/s]
15%|#5 | 25.6M/170M [00:00<00:01, 112MB/s]
21%|##1 | 36.5M/170M [00:00<00:01, 107MB/s]
28%|##7 | 46.8M/170M [00:00<00:01, 104MB/s]
33%|###3 | 56.8M/170M [00:00<00:01, 95.2MB/s]
40%|#### | 68.7M/170M [00:00<00:01, 104MB/s]
46%|####6 | 78.8M/170M [00:00<00:00, 103MB/s]
52%|#####2 | 88.7M/170M [00:00<00:00, 102MB/s]
58%|#####7 | 98.5M/170M [00:00<00:00, 101MB/s]
64%|######3 | 108M/170M [00:01<00:00, 101MB/s]
69%|######9 | 118M/170M [00:01<00:00, 101MB/s]
75%|#######5 | 127M/170M [00:01<00:00, 100MB/s]
81%|######## | 137M/170M [00:01<00:00, 100MB/s]
86%|########6 | 147M/170M [00:01<00:00, 100MB/s]
92%|#########1| 156M/170M [00:01<00:00, 100MB/s]
98%|#########7| 166M/170M [00:01<00:00, 100MB/s]
100%|##########| 170M/170M [00:01<00:00, 102MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 19.523 seconds)
+ **Total running time of the script:** ( 3 minutes 14.858 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 2656ce267f..f50cf0c760 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -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)
- 90.3967 90.2581 94.7032 90.0214 0.5918
+ 90.5660 90.2833 101.4373 90.0897 1.2687
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.853 seconds)
+ **Total running time of the script:** ( 1 minutes 6.665 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 4c11dc3e24..fee4996e3b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.3716 121.3126 124.8323 120.6581 0.4649
+ 121.8195 121.7278 127.9332 121.0439 0.7270
@@ -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 23.806 seconds)
+ **Total running time of the script:** ( 2 minutes 23.053 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 113b4c1678..5550ae91f5 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 13.738 seconds)
+ **Total running time of the script:** ( 1 minutes 14.265 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 ace9826117..f5f866b570 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]
5%|5 | 6655/132723 [00:00<00:01, 66545.78KB/s]
11%|#1 | 14614/132723 [00:00<00:01, 74196.11KB/s]
17%|#7 | 22632/132723 [00:00<00:01, 76926.60KB/s]
23%|##3 | 30612/132723 [00:00<00:01, 78057.94KB/s]
29%|##9 | 38541/132723 [00:00<00:01, 78501.00KB/s]
35%|###5 | 46511/132723 [00:00<00:01, 78905.33KB/s]
41%|####1 | 54524/132723 [00:00<00:00, 79303.41KB/s]
47%|####7 | 62574/132723 [00:00<00:00, 79681.74KB/s]
53%|#####3 | 70593/132723 [00:00<00:00, 79838.86KB/s]
59%|#####9 | 78697/132723 [00:01<00:00, 80199.29KB/s]
65%|######5 | 86761/132723 [00:01<00:00, 80323.98KB/s]
71%|#######1 | 94864/132723 [00:01<00:00, 80534.94KB/s]
78%|#######7 | 102918/132723 [00:01<00:00, 80510.92KB/s]
84%|########3 | 110985/132723 [00:01<00:00, 80552.89KB/s]
90%|########9 | 119041/132723 [00:01<00:00, 79672.50KB/s]
96%|########
#5| 127011/132723 [00:01<00:00, 79131.08KB/s]
100%|##########| 132723/132723 [00:01<00:00, 79050.52KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4011/132723 [00:00<00:03, 40107.17KB/s]
9%|9 | 12129/132723 [00:00<00:01, 64264.74KB/s]
16%|#5 | 21025/132723 [00:00<00:01, 75525.46KB/s]
23%|##2 | 29965/132723 [00:00<00:01, 80999.55KB/s]
29%|##9 | 38785/132723 [00:00<00:01, 82595.52KB/s]
36%|###5 | 47688/132723 [00:00<00:01, 84756.63KB/s]
43%|####2 | 56538/132723 [00:00<00:00, 85972.02KB/s]
49%|####9 | 65430/132723 [00:00<00:00, 86905.71KB/s]
56%|#####6 | 74371/132723 [00:00<00:00, 87683.98KB/s]
63%|######2 | 83271/132723 [00:01<00:00, 88088.19KB/s]
69%|######9 | 92081/132723 [00:01<00:00, 87848.74KB/s]
76%|#######6 | 100898/132723 [00:01<00:00, 87944.95KB/s]
83%|########2 | 109693/132723 [00:01<00:00, 87524.93KB/s]
89%|########9 | 118447/132723 [00:01<00:00, 87018.68KB/s]
96%|#########5| 127150/132723 [00:01<00:00, 86731.30KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84210.72KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 58.324 seconds)
+ **Total running time of the script:** ( 3 minutes 2.922 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 e14f3fa8e5..3f69462466 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
=================
-**12:27.573** total execution time for **how_to_deploy_models** files:
+**12:26.487** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:19.523 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:14.858 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:58.324 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:02.922 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:23.806 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:23.053 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:13.738 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:14.265 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.853 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.665 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.593 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.485 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.228 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.869 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.502 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.364 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 9d73e2397c..ff7abd224b 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.zipa864aaa3-d1e7-4acb-928a-1c4a408622a7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip6032e6aa-cae1-43fb-9d47-412ec80214e1 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 9d81d714ad..76c0f1b128 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
=================
-**00:48.240** total execution time for **how_to_extend_tvm** files:
+**00:48.452** 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``) | 00:44.766 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.959 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.426 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.440 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.046 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 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 f4cb589cf8..b40281adf2 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: 6912us [6912us] (47.46%; 47.46%)
- FoldScaleAxis: 7653us [5us] (52.54%; 52.54%)
- FoldConstant: 7648us [1559us] (52.51%; 99.93%)
- InferType: 6088us [6088us] (41.80%; 79.61%)
+ InferType: 6689us [6689us] (46.46%; 46.46%)
+ FoldScaleAxis: 7707us [6us] (53.54%; 53.54%)
+ FoldConstant: 7701us [1528us] (53.50%; 99.93%)
+ InferType: 6173us [6173us] (42.88%; 80.15%)
@@ -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: 6122us [6122us] (44.72%; 44.72%)
- FoldScaleAxis: 7568us [5us] (55.28%; 55.28%)
- FoldConstant: 7564us [1541us] (55.25%; 99.94%)
- InferType: 6023us [6023us] (43.99%; 79.63%)
+ InferType: 6139us [6139us] (44.79%; 44.79%)
+ FoldScaleAxis: 7567us [5us] (55.21%; 55.21%)
+ FoldConstant: 7563us [1536us] (55.18%; 99.94%)
+ InferType: 6027us [6027us] (43.97%; 79.69%)
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 fddbff7dab..0bf088acfc 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: 36.620414 ms
+ Convolution: 35.050209 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 a04efad1ed..a0efeafac4 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: 12.418589 ms
+ conv2d with tensor core: 13.358694 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 58ca69954a..580c5049d5 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: 0.018290
- Baseline: 3.393212
+ Numpy running time: 0.019383
+ Baseline: 3.343131
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.302268
+ Opt1: 0.300793
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.327429
+ Opt2: 0.333112
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118018
+ Opt3: 0.116146
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110064
+ Opt4: 0.109314
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111293
+ Opt5: 0.115390
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147344
+ Opt6: 0.152871
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 2baa3516d4..7747ea992c 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
=================
-**00:34.790** total execution time for **how_to_optimize_operators** files:
+**00:35.186** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.180 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.515 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.461 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.561 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.149 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.110 | 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 c998ceaaa7..1d3d2afa5c 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
=================
-**09:04.325** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:07.578** 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``) | 05:34.905 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:40.928 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.231 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.351 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.278 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.894 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.452 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.501 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.198 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.851 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.261 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.054 | 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 8cc4a7f049..c24540ef91 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
@@ -240,12 +240,12 @@ 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" = 28;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), 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" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[8] = 0f32
@@ -259,431 +259,380 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 9)*7)) + (floormod(blockIdx.x, 7)*7 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 10), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 10), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod( [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 20), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 20), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 3), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod [...]
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[ramp((threadIdx.x_2*3), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 192), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 384), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 576), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 36864), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 768), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 960), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1152), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 73728), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1344), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1536), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1728), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 110592), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1920), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2112), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2304), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 147456), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2496), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2688), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2880), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 184320), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3072), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3264), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3456), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 221184), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3648), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3840), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4032), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 258048), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4224), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4416), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4608), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 294912), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4800), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4992), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5184), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 331776), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5376), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5568), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5760), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 368640), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5952), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6144), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6336), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 405504), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6528), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6720), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6912), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 442368), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7104), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7296), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7488), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 479232), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7680), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7872), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8064), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 516096), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8256), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8448), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8640), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 552960), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8832), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 9024), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- for (rc.outer.inner: int32, 0, 4) {
- let cse_var_56: int32 = (rc.outer.inner*54)
- let cse_var_55: int32 = (cse_var_56 + 9)
- let cse_var_54: int32 = (cse_var_56 + 8)
- let cse_var_53: int32 = (cse_var_56 + 7)
- let cse_var_52: int32 = (cse_var_56 + 6)
- let cse_var_51: int32 = (cse_var_56 + 53)
- let cse_var_50: int32 = (cse_var_56 + 52)
- let cse_var_49: int32 = (cse_var_56 + 51)
- let cse_var_48: int32 = (cse_var_56 + 50)
- let cse_var_47: int32 = (cse_var_56 + 5)
- let cse_var_46: int32 = (cse_var_56 + 49)
- let cse_var_45: int32 = (cse_var_56 + 48)
- let cse_var_44: int32 = (cse_var_56 + 47)
- let cse_var_43: int32 = (cse_var_56 + 46)
- let cse_var_42: int32 = (cse_var_56 + 45)
- let cse_var_41: int32 = (cse_var_56 + 44)
- let cse_var_40: int32 = (cse_var_56 + 43)
- let cse_var_39: int32 = (cse_var_56 + 42)
- let cse_var_38: int32 = (cse_var_56 + 41)
- let cse_var_37: int32 = (cse_var_56 + 40)
- let cse_var_36: int32 = (cse_var_56 + 4)
- let cse_var_35: int32 = (cse_var_56 + 39)
- let cse_var_34: int32 = (cse_var_56 + 38)
- let cse_var_33: int32 = (cse_var_56 + 37)
- let cse_var_32: int32 = (cse_var_56 + 36)
- let cse_var_31: int32 = (cse_var_56 + 35)
- let cse_var_30: int32 = (cse_var_56 + 34)
- let cse_var_29: int32 = (cse_var_56 + 33)
- let cse_var_28: int32 = (cse_var_56 + 32)
- let cse_var_27: int32 = (cse_var_56 + 31)
- let cse_var_26: int32 = (cse_var_56 + 30)
- let cse_var_25: int32 = (cse_var_56 + 3)
- let cse_var_24: int32 = (cse_var_56 + 29)
- let cse_var_23: int32 = (cse_var_56 + 28)
- let cse_var_22: int32 = (cse_var_56 + 27)
- let cse_var_21: int32 = (cse_var_56 + 26)
- let cse_var_20: int32 = (cse_var_56 + 25)
- let cse_var_19: int32 = (cse_var_56 + 24)
- let cse_var_18: int32 = (cse_var_56 + 23)
- let cse_var_17: int32 = (cse_var_56 + 22)
- let cse_var_16: int32 = (cse_var_56 + 21)
- let cse_var_15: int32 = (cse_var_56 + 20)
- let cse_var_14: int32 = (cse_var_56 + 2)
- let cse_var_13: int32 = (cse_var_56 + 19)
- let cse_var_12: int32 = (cse_var_56 + 18)
- let cse_var_11: int32 = (cse_var_56 + 17)
- let cse_var_10: int32 = (cse_var_56 + 16)
- let cse_var_9: int32 = (cse_var_56 + 15)
- let cse_var_8: int32 = (cse_var_56 + 14)
- let cse_var_7: int32 = (cse_var_56 + 13)
- let cse_var_6: int32 = (cse_var_56 + 12)
- let cse_var_5: int32 = (cse_var_56 + 11)
- let cse_var_4: int32 = (cse_var_56 + 10)
- let cse_var_3: int32 = (cse_var_56 + 1)
- {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
+ for (rc.outer.outer: int32, 0, 16) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_4: int32 = (rc.outer.outer*1568)
+ let cse_var_3: int32 = (rc.outer.outer*288)
+ let cse_var_2: int32 = (ry.outer.outer*7)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*32)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*32), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*32), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) - 8)], 0f32, dtyp [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 2), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 2), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 2), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 3), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 3), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 3), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 4)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 4), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 5)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 5), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 5), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 5), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 6)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 6), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 6), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 6), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 7)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 7), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 8)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 8), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 8), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 8), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 9)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 1), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 1), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) - 1)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 10)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 10), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 10), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 10), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 11)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 11), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 11), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 11), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 12)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 12), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 12), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 12), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 13)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 13), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 13), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 13), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 14)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 14), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 15)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 15), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 15), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 15), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 16)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 16), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 16), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 16), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 17)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 17), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 17), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 17), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 18)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 2), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 2), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 19)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 19), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 19), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 19), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 20)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 20), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 20), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 20), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 21)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 21), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 22)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 22), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 22), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 22), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 23)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 23), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 23), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 23), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 24)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 24), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 24), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 24), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 25)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 25), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 25), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 25), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 26)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 26), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 26), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 26), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 27)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 3), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 3), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 13)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 28)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 28), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 29)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 29), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 29), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 29), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 30)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 30), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 30), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 30), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 31)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 31), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 31), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 31), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1792), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1793)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 29), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 29), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1793), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1794)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 30), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 30), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1794), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1795)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 31), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 31), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1795), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1796)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 32), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 32), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1796), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1797)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 33), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 33), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1797), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1798)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 34), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 34), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1798), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1799)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1799), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1800)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 4), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 4), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 1392)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1801)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 1), 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1792), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - 1)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1802)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 38), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 38), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1802), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1803)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 39), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 39), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1803), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1804)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 40), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 40), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1804), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1805)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 41), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 41), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1805), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1806)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1806), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1807)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 43), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 43), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1807), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1808)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 44), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 44), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1808), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1809)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 5), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 5), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 1399)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1810)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 2), 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1792), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) + 6)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1811)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 47), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 47), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1811), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1812)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 48), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 48), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1812), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1813)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1813), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1814)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 50), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 50), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1814), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1815)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 51), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 51), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1815), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1816)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 52), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 52), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1816), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1817)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 53), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 53), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1817), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1818)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 6), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 6), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 1406)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1819)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 3), 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1792), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) + 13)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1820)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1820), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1821)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 57), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 57), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1821), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1822)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 58), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 58), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1822), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1823)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 59), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 59), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1823), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_3) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*73728) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_3) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*73728) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_3) + ((floordiv(threadIdx.x_2, 3) + 24)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ }
+ for (rc.outer.inner: int32, 0, 8) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
}
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner) + 3136)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -738,7 +687,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.275 ms
+ Execution time of this operator: 0.334 ms
@@ -786,33 +735,33 @@ 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=64)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=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=7)
- 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_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_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=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)
@@ -833,14 +782,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
+ 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=64)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=32)
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=64)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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)
@@ -860,10 +809,10 @@ 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__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[216];
- __shared__ float kernel_shared[9216];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -878,321 +827,344 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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 < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] [...]
- if (((int)threadIdx.x) < 24) {
- pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= (((((int)threadIdx.x) + 3) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) + 3) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- *(float3*)(kernel_shared + (((int)threadIdx.x) * 3)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 192)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 384)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 576)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 36864));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 768)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 960)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1152)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 73728));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1344)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1536)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1728)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 110592));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1920)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2112)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2304)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 147456));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2496)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2688)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2880)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 184320));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3072)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3264)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3456)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 221184));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3648)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3840)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4032)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 258048));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4224)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4416)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4608)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 294912));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4800)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4992)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5184)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 331776));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5376)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5568)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5760)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 368640));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5952)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6144)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6336)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 405504));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6528)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6720)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6912)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 442368));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7104)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7296)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7488)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 479232));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7680)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7872)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8064)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 516096));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8256)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8448)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8640)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 552960));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8832)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 9024)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rc_outer_inner * 54)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(rc_outer_inner * 54)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 1)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 53)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 53)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 32)] = (((((1 <= ((((((int)threadIdx.x) * 32) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 32) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 2) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 3) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 4) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 4) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 5) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 5) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 5) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 6)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 6) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 6) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 6) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 7) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 8)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 8) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 9)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 1) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 10)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 10) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 10) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 10) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 11)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 11) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 11) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 11) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 12)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 12) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 12) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 12) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 13)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 13) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 13) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 13) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 14)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 14) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 15)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 15) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 16)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 16) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 16) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 17)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 17) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 17) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 17) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 18)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 2) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 2) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 19)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 19) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 19) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 19) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 20)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 20) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 20) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 20) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 21)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 21) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 22)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 22) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 23)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 23) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 23) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 23) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 24)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 24) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 24) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 24) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 25)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 25) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 25) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 25) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 26)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 26) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 26) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 26) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 27)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 3) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 3) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 13)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 28)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 28) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 29)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 29) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 30)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 30) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 31)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 31) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1792)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1793)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1793) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1794)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1794) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1795)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1795) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1796)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 32) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 32) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1796) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1797)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 33) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 33) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1797) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1798)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 34) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 34) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1798) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1799)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1799) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1800)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 1392)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1801)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 1) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 1)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1802)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 38) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 38) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1802) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1803)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 39) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 39) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1803) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1804)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 40) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 40) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1804) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1805)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 41) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 41) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1805) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1806)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1806) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1807)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1807) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1808)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 44) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 44) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1808) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1809)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 5) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 1399)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1810)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 2) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 2) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) + 6)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1811)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 47) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 47) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1811) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1812)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 48) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 48) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1812) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1813)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1813) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1814)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1814) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1815)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 51) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 51) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1815) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1816)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 52) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 52) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1816) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1817)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 53) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 53) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1817) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1818)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 6) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 6) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 1406)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1819)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 3) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 3) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) + 13)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1820)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1820) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1821)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1821) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1822)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 58) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 58) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1822) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1823)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 59) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 59) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1823) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 216)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ }
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner) + 3136)] = max((conv2d_nchw[(i3_inner + 7)] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -1254,7 +1226,7 @@ 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 34.905 seconds)
+ **Total running time of the script:** ( 5 minutes 40.928 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 98a6c9bff3..7c3d2875e5 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)
- 8.2064 8.2100 8.2109 8.1983 0.0057
+ 8.1756 8.1743 8.1839 8.1687 0.0063
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.278 seconds)
+ **Total running time of the script:** ( 1 minutes 2.894 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 6ce2c2b6ed..c783f741cb 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)
- 755.5367 757.3368 758.8554 750.4179 3.6723
+ 754.8082 753.9005 756.9295 753.5945 1.5052
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.231 seconds)
+ **Total running time of the script:** ( 1 minutes 32.351 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 3f6428b178..5d5928a191 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
@@ -386,217 +386,106 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [512], [])[cse_var_2] = 0f32
- compute_5[(cse_var_2 + 1)] = 0f32
- compute_5[(cse_var_2 + 2)] = 0f32
- compute_5[(cse_var_2 + 3)] = 0f32
- compute_5[(cse_var_2 + 4)] = 0f32
- compute_5[(cse_var_2 + 5)] = 0f32
- compute_5[(cse_var_2 + 6)] = 0f32
- compute_5[(cse_var_2 + 7)] = 0f32
- compute_5[(cse_var_2 + 8)] = 0f32
- compute_5[(cse_var_2 + 9)] = 0f32
- compute_5[(cse_var_2 + 10)] = 0f32
- compute_5[(cse_var_2 + 11)] = 0f32
- compute_5[(cse_var_2 + 12)] = 0f32
- compute_5[(cse_var_2 + 13)] = 0f32
- compute_5[(cse_var_2 + 14)] = 0f32
- compute_5[(cse_var_2 + 15)] = 0f32
- compute_5[(cse_var_2 + 32)] = 0f32
- compute_5[(cse_var_2 + 33)] = 0f32
- compute_5[(cse_var_2 + 34)] = 0f32
- compute_5[(cse_var_2 + 35)] = 0f32
- compute_5[(cse_var_2 + 36)] = 0f32
- compute_5[(cse_var_2 + 37)] = 0f32
- compute_5[(cse_var_2 + 38)] = 0f32
- compute_5[(cse_var_2 + 39)] = 0f32
- compute_5[(cse_var_2 + 40)] = 0f32
- compute_5[(cse_var_2 + 41)] = 0f32
- compute_5[(cse_var_2 + 42)] = 0f32
- compute_5[(cse_var_2 + 43)] = 0f32
- compute_5[(cse_var_2 + 44)] = 0f32
- compute_5[(cse_var_2 + 45)] = 0f32
- compute_5[(cse_var_2 + 46)] = 0f32
- compute_5[(cse_var_2 + 47)] = 0f32
- compute_5[(cse_var_2 + 64)] = 0f32
- compute_5[(cse_var_2 + 65)] = 0f32
- compute_5[(cse_var_2 + 66)] = 0f32
- compute_5[(cse_var_2 + 67)] = 0f32
- compute_5[(cse_var_2 + 68)] = 0f32
- compute_5[(cse_var_2 + 69)] = 0f32
- compute_5[(cse_var_2 + 70)] = 0f32
- compute_5[(cse_var_2 + 71)] = 0f32
- compute_5[(cse_var_2 + 72)] = 0f32
- compute_5[(cse_var_2 + 73)] = 0f32
- compute_5[(cse_var_2 + 74)] = 0f32
- compute_5[(cse_var_2 + 75)] = 0f32
- compute_5[(cse_var_2 + 76)] = 0f32
- compute_5[(cse_var_2 + 77)] = 0f32
- compute_5[(cse_var_2 + 78)] = 0f32
- compute_5[(cse_var_2 + 79)] = 0f32
- compute_5[(cse_var_2 + 96)] = 0f32
- compute_5[(cse_var_2 + 97)] = 0f32
- compute_5[(cse_var_2 + 98)] = 0f32
- compute_5[(cse_var_2 + 99)] = 0f32
- compute_5[(cse_var_2 + 100)] = 0f32
- compute_5[(cse_var_2 + 101)] = 0f32
- compute_5[(cse_var_2 + 102)] = 0f32
- compute_5[(cse_var_2 + 103)] = 0f32
- compute_5[(cse_var_2 + 104)] = 0f32
- compute_5[(cse_var_2 + 105)] = 0f32
- compute_5[(cse_var_2 + 106)] = 0f32
- compute_5[(cse_var_2 + 107)] = 0f32
- compute_5[(cse_var_2 + 108)] = 0f32
- compute_5[(cse_var_2 + 109)] = 0f32
- compute_5[(cse_var_2 + 110)] = 0f32
- compute_5[(cse_var_2 + 111)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- let cse_var_67: int32 = (elem_idx*16)
- let cse_var_66: int32 = (cse_var_2 + 99)
- let cse_var_65: int32 = (cse_var_2 + 98)
- let cse_var_64: int32 = (cse_var_2 + 97)
- let cse_var_63: int32 = (cse_var_2 + 96)
- let cse_var_62: int32 = (cse_var_2 + 9)
- let cse_var_61: int32 = (cse_var_2 + 8)
- let cse_var_60: int32 = (cse_var_2 + 79)
- let cse_var_59: int32 = (cse_var_2 + 78)
- let cse_var_58: int32 = (cse_var_2 + 77)
- let cse_var_57: int32 = (cse_var_2 + 76)
- let cse_var_56: int32 = (cse_var_2 + 75)
- let cse_var_55: int32 = (cse_var_2 + 74)
- let cse_var_54: int32 = (cse_var_2 + 73)
- let cse_var_53: int32 = (cse_var_2 + 72)
- let cse_var_52: int32 = (cse_var_2 + 71)
- let cse_var_51: int32 = (cse_var_2 + 70)
- let cse_var_50: int32 = (cse_var_2 + 7)
- let cse_var_49: int32 = (cse_var_2 + 69)
- let cse_var_48: int32 = (cse_var_2 + 68)
- let cse_var_47: int32 = (cse_var_2 + 67)
- let cse_var_46: int32 = (cse_var_2 + 66)
- let cse_var_45: int32 = (cse_var_2 + 65)
- let cse_var_44: int32 = (cse_var_2 + 64)
- let cse_var_43: int32 = (cse_var_2 + 6)
- let cse_var_42: int32 = (cse_var_2 + 5)
- let cse_var_41: int32 = (cse_var_2 + 47)
- let cse_var_40: int32 = (cse_var_2 + 46)
- let cse_var_39: int32 = (cse_var_2 + 45)
- let cse_var_38: int32 = (cse_var_2 + 44)
- let cse_var_37: int32 = (cse_var_2 + 43)
- let cse_var_36: int32 = (cse_var_2 + 42)
- let cse_var_35: int32 = (cse_var_2 + 41)
- let cse_var_34: int32 = (cse_var_2 + 40)
- let cse_var_33: int32 = (cse_var_2 + 4)
- let cse_var_32: int32 = (cse_var_2 + 39)
- let cse_var_31: int32 = (cse_var_2 + 38)
- let cse_var_30: int32 = (cse_var_2 + 37)
- let cse_var_29: int32 = (cse_var_2 + 36)
- let cse_var_28: int32 = (cse_var_2 + 35)
- let cse_var_27: int32 = (cse_var_2 + 34)
- let cse_var_26: int32 = (cse_var_2 + 33)
- let cse_var_25: int32 = (cse_var_2 + 32)
- let cse_var_24: int32 = (cse_var_2 + 3)
- let cse_var_23: int32 = (cse_var_2 + 2)
- let cse_var_22: int32 = (cse_var_2 + 15)
- let cse_var_21: int32 = (cse_var_2 + 14)
- let cse_var_20: int32 = (cse_var_2 + 13)
- let cse_var_19: int32 = (cse_var_2 + 12)
- let cse_var_18: int32 = (cse_var_2 + 111)
- let cse_var_17: int32 = (cse_var_2 + 110)
- let cse_var_16: int32 = (cse_var_2 + 11)
- let cse_var_15: int32 = (cse_var_2 + 109)
- let cse_var_14: int32 = (cse_var_2 + 108)
- let cse_var_13: int32 = (cse_var_2 + 107)
- let cse_var_12: int32 = (cse_var_2 + 106)
- let cse_var_11: int32 = (cse_var_2 + 105)
- let cse_var_10: int32 = (cse_var_2 + 104)
- let cse_var_9: int32 = (cse_var_2 + 103)
- let cse_var_8: int32 = (cse_var_2 + 102)
- let cse_var_7: int32 = (cse_var_2 + 101)
- let cse_var_6: int32 = (cse_var_2 + 100)
- let cse_var_5: int32 = (cse_var_2 + 10)
- let cse_var_4: int32 = (cse_var_2 + 1)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*1024))
- {
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_67)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 32) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ {
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*512) + (i.inner*16))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_68: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_68, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -652,7 +541,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 3.042 ms
+ Execution time of this operator: 2.021 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 84c5312396..b36014a199 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:31.072** total execution time for **how_to_tune_with_autotvm** files:
+**00:32.939** 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``) | 00:31.037 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:32.904 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 e211b660cc..3c252560d0 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -265,8 +265,26 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 17.24/17.24 result: MeasureResult(costs=(0.013425095444444445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.040456771850586, timestamp=1667929722.8924406) [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6074367
- No: 2 GFLOPS: 0.00/17.24 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 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, 2, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4046349
+ No: 2 GFLOPS: 273.34/273.34 result: MeasureResult(costs=(0.0008469235,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.00227689743042, timestamp=1667930513.777336) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1764867
+ No: 3 GFLOPS: 0.00/273.34 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
@@ -388,8 +406,8 @@ 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, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9636837
- No: 3 GFLOPS: 0.00/17.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4988951
+ No: 4 GFLOPS: 0.00/273.34 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
@@ -511,9 +529,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2486608
- No: 4 GFLOPS: 3.69/17.24 result: MeasureResult(costs=(0.0628082655,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.670874834060669, timestamp=1667929724.9528527) [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5517272
- No: 5 GFLOPS: 0.00/17.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8220121
+ No: 5 GFLOPS: 0.00/273.34 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
@@ -635,8 +652,8 @@ 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, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5788005
- No: 6 GFLOPS: 0.00/17.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1098987
+ No: 6 GFLOPS: 0.00/273.34 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
@@ -758,8 +775,8 @@ 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, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3651387
- No: 7 GFLOPS: 0.00/17.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5468477
+ No: 7 GFLOPS: 0.00/273.34 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
@@ -881,9 +898,8 @@ 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8161895
- No: 8 GFLOPS: 91.85/91.85 result: MeasureResult(costs=(0.0025205581860465115,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4904000759124756, timestamp=1667929728.4538808) [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3101383
- No: 9 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4711036
+ No: 8 GFLOPS: 0.00/273.34 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
@@ -1005,8 +1021,8 @@ 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, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,379665
- No: 10 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3919317
+ No: 9 GFLOPS: 0.00/273.34 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
@@ -1128,8 +1144,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8672709
- No: 11 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9480179
+ No: 10 GFLOPS: 0.00/273.34 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
@@ -1251,8 +1267,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1044097
- No: 12 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4131591
+ No: 11 GFLOPS: 0.00/273.34 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
@@ -1374,8 +1390,8 @@ 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, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,644049
- No: 13 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6324935
+ No: 12 GFLOPS: 0.00/273.34 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
@@ -1497,9 +1513,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9275568
- No: 14 GFLOPS: 0.87/91.85 result: MeasureResult(costs=(0.26746337875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.2179131507873535, timestamp=1667929734.0918875) [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,247665
- No: 15 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1694286
+ No: 13 GFLOPS: 0.00/273.34 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
@@ -1621,8 +1636,8 @@ 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, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1262849
- No: 16 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6253237
+ No: 14 GFLOPS: 0.00/273.34 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
@@ -1744,8 +1759,9 @@ 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, 4, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8850976
- No: 17 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7223233
+ No: 15 GFLOPS: 152.68/273.34 result: MeasureResult(costs=(0.0015162880138888887,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6183815002441406, timestamp=1667930519.9783366) [('tile_f', [-1, 1, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7014435
+ No: 16 GFLOPS: 0.00/273.34 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
@@ -1867,8 +1883,8 @@ 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, 2, 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', 1500), ('unroll_explicit', 1)],None,10065585
- No: 18 GFLOPS: 0.00/91.85 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, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3928914
+ No: 17 GFLOPS: 0.00/273.34 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
@@ -1990,8 +2006,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2437712
- No: 19 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7004638
+ No: 18 GFLOPS: 0.00/273.34 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
@@ -2113,8 +2129,131 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9454711
- No: 20 GFLOPS: 3.97/91.85 result: MeasureResult(costs=(0.058333782,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9448578357696533, timestamp=1667929737.288313) [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3680068
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3410216
+ No: 19 GFLOPS: 154.11/273.34 result: MeasureResult(costs=(0.001502168328358209,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4731054306030273, timestamp=1667930521.6758177) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3004604
+ No: 20 GFLOPS: 0.00/273.34 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, 128, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10083367
@@ -2169,9 +2308,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3101383
+ [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1764867
Finish loading 20 records
- Time cost of this operator: 0.001876
+ Time cost of this operator: 0.001088
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 2845560fe7..3bcee40c5a 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 98.715 (1, 2, 10, 10, 3) 2 1 [311.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.973 (1, 6, 10, 10) 1 1 [3.066]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.986 0.313 (1, 1, 10, 10, 3) 1 1 [0.986]
- Total_time - 315.151 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.5 98.735 (1, 2, 10, 10, 3) 2 1 [312.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.045 0.962 (1, 6, 10, 10) 1 1 [3.045]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.959 0.303 (1, 1, 10, 10, 3) 1 1 [0.959]
+ Total_time - 316.504 - - - - -
@@ -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 134.9 97.986 (1, 6, 10, 10, 1) 2 1 [134.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.809 1.314 (1, 6, 10, 10) 1 1 [1.809]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.7 (1, 1, 10, 10, 3) 1 1 [0.964]
- Total_time - 137.673 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.4 97.396 (1, 6, 10, 10, 1) 2 1 [102.4]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.771 1.684 (1, 6, 10, 10) 1 1 [1.771]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 0.919 (1, 1, 10, 10, 3) 1 1 [0.967]
+ Total_time - 105.138 - - - - -
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 e8c05f6894..4f8a2f165e 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/tmp9l3zdfow/images/random'
+ '/tmp/tmpdvy0vmfd/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], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
+ :alt: [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp9l3zdfow/images/target contains 8144 images
- /tmp/tmp9l3zdfow/images/random contains 5000 images
+ /tmp/tmpdvy0vmfd/images/target contains 8144 images
+ /tmp/tmpdvy0vmfd/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 46s - loss: 0.2186 - accuracy: 0.9260 - val_loss: 0.1653 - val_accuracy: 0.9517 - 46s/epoch - 142ms/step
+ 328/328 - 46s - loss: 0.2163 - accuracy: 0.9264 - val_loss: 0.1278 - val_accuracy: 0.9619 - 46s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0979 - accuracy: 0.9619 - val_loss: 0.1414 - val_accuracy: 0.9524 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0935 - accuracy: 0.9658 - val_loss: 0.1236 - val_accuracy: 0.9603 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0731 - accuracy: 0.9716 - val_loss: 0.1817 - val_accuracy: 0.9471 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0706 - accuracy: 0.9722 - val_loss: 0.1269 - val_accuracy: 0.9637 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f5fbe251d50>
+ <keras.callbacks.History object at 0x7fde58700c90>
@@ -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 0.565 seconds)
+ **Total running time of the script:** ( 4 minutes 19.574 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 74e002a702..e90009cc97 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**05:01.578** total execution time for **how_to_work_with_microtvm** files:
+**05:19.873** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:00.565 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:19.574 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.303 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:48.919 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.656 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.681 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.722 | 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 7e99014926..d91abb9e40 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
=================
-**00:43.246** total execution time for **how_to_work_with_relay** files:
+**00:44.004** 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``) | 00:31.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.054 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.169 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.251 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.541 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.692 | 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 2a87cf5ad1..71850308a0 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 0x7f5f5e3f0c20>
+ <function my_cuda_math_rule at 0x7fde0207b5f0>
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 0e0ba17ba7..cadfcc278f 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
=================
-**00:06.210** total execution time for **how_to_work_with_schedules** files:
+**00:05.738** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:03.881 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:03.410 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.030 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.005 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.566 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.537 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.545 | 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``) | 00:00.048 | 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``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 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 d349a15d6c..7dbd7ef834 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/tmpuvwaf5gp/input0.cc'\nsource_filename = \"/tmp/tmpuvwaf5gp/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/tmpfclfy8je/input0.cc'\nsource_filename = \"/tmp/tmpfclfy8je/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 472c53bd34..efafe936b7 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
=================
-**00:26.453** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.251** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.447 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.244 | 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 3bb315d604..d13ceea2c3 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 29.71s!
+ resnet18_v1 inference graph built in 29.85s!
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 831615631c..4d936779aa 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 19.77s!
+ yolov3-tiny inference graph built in 20.14s!
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 8ba8dd91cf..1fd932b3ff 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
=================
-**01:40.819** total execution time for **topic_vta_tutorials_frontend** files:
+**01:41.408** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.309 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.590 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.510 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.818 | 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 52bb1c010f..8031d3aa55 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
=================
-**00:03.116** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.121** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.684 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.673 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.433 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.449 | 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 ceab28df9a..d90f8a1549 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
=================
-**00:00.784** total execution time for **topic_vta_tutorials** files:
+**00:00.785** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.415 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.418 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.369 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.367 | 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 8b5c24bcdc..160c6bdf9a 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
-
-
@@ -333,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 97.901 ms
+ Execution time of this operator: 94.309 ms
@@ -433,7 +426,7 @@ 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
+
@@ -451,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.374 seconds)
+ **Total running time of the script:** ( 1 minutes 12.380 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 f97d6e9861..6b6eb30937 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: 10.94/10.94 result: MeasureResult(costs=(0.0245441248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6051483154296875, timestamp=1667928363.5591667) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
- No: 2 GFLOPS: 0.50/10.94 result: MeasureResult(costs=(0.5351993628,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.729020833969116, timestamp=1667928372.3072314) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
- No: 3 GFLOPS: 12.87/12.87 result: MeasureResult(costs=(0.020857743199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5411012172698975, timestamp=1667928373.5491374) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
- No: 4 GFLOPS: 0.90/12.87 result: MeasureResult(costs=(0.2995044662,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.939200162887573, timestamp=1667928378.5030456) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
- No: 5 GFLOPS: 2.16/12.87 result: MeasureResult(costs=(0.12419423380000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1458237171173096, timestamp=1667928380.7700942) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
- No: 6 GFLOPS: 3.03/12.87 result: MeasureResult(costs=(0.08850243220000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5829555988311768, timestamp=1667928383.118172) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
- No: 7 GFLOPS: 1.46/12.87 result: MeasureResult(costs=(0.183464197,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.087735414505005, timestamp=1667928386.9748073) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 8 GFLOPS: 12.03/12.87 result: MeasureResult(costs=(0.022319072000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5626184940338135, timestamp=1667928387.5537179) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
- No: 9 GFLOPS: 1.54/12.87 result: MeasureResult(costs=(0.1743451912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.924138069152832, timestamp=1667928390.8104784) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
- No: 10 GFLOPS: 9.74/12.87 result: MeasureResult(costs=(0.027557288999999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8015899658203125, timestamp=1667928391.4209356) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+ No: 1 GFLOPS: 3.31/3.31 result: MeasureResult(costs=(0.0810645858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4697649478912354, timestamp=1667929171.7026908) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
+ No: 2 GFLOPS: 13.36/13.36 result: MeasureResult(costs=(0.0200879916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5213887691497803, timestamp=1667929172.949474) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
+ No: 3 GFLOPS: 3.15/13.36 result: MeasureResult(costs=(0.08508645540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.513859748840332, timestamp=1667929175.2222762) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
+ No: 4 GFLOPS: 9.82/13.36 result: MeasureResult(costs=(0.0273386124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5807535648345947, timestamp=1667929175.8264558) [('tile_y', [-1, 2]), ('tile_x', [-1, 32])],None,51
+ No: 5 GFLOPS: 12.47/13.36 result: MeasureResult(costs=(0.0215216234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5087535381317139, timestamp=1667929176.4627697) [('tile_y', [-1, 128]), ('tile_x', [-1, 256])],None,87
+ No: 6 GFLOPS: 0.46/13.36 result: MeasureResult(costs=(0.5822482323999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.480411529541016, timestamp=1667929185.9742908) [('tile_y', [-1, 512]), ('tile_x', [-1, 1])],None,9
+ No: 7 GFLOPS: 10.23/13.36 result: MeasureResult(costs=(0.0262322748,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5583615303039551, timestamp=1667929187.3201284) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 8 GFLOPS: 0.90/13.36 result: MeasureResult(costs=(0.2995719126,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.9787445068359375, timestamp=1667929192.317788) [('tile_y', [-1, 128]), ('tile_x', [-1, 2])],None,17
+ No: 9 GFLOPS: 1.76/13.36 result: MeasureResult(costs=(0.1526136742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.569279909133911, timestamp=1667929195.0051718) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+ No: 10 GFLOPS: 3.55/13.36 result: MeasureResult(costs=(0.07568241719999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3339037895202637, timestamp=1667929196.3810997) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 1a0a94d516..0241edf051 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': 516.4690437500008, 'median': 516.2654152999949, 'std': 1.9471380053512977}
+ {'mean': 523.8234768699988, 'median': 524.8220038499994, 'std': 3.2826715339377572}
@@ -554,29 +554,30 @@ 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: 21.77/ 21.77 GFLOPS | Progress: (4/20) | 6.93 s
[Task 1/25] Current/Best: 18.85/ 21.77 GFLOPS | Progress: (8/20) | 11.39 s
[Task 1/25] Current/Best: 9.94/ 21.77 GFLOPS | Progress: (12/20) | 13.82 s
[Task 1/25] Current/Best: 23.22/ 23.22 GFLOPS | Progress: (16/20) | 16.47 s
[Task 1/25] Current/Best: 18.93/ 23.22 GFLOPS | Progress: (20/20) | 19.99 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 6.43/ 22.67 GFLOPS | Progress: (4/20) | 2.83 s
[Task 2/25] Current/Best: 19.22/ 22.67 GFLOPS | Progress: (8/20) | 3.83 s
[Task 2/25] Current/Best: 7.90/ 22.67 GFLOPS | Progress: (12/20) | 5.01 s
[Task 2/25] Current/Best: 8.63/ 22.67 GFLOPS | Progress: (16/20) | 6.64 s
[Task 2/25] Current/Best: 8.51/ 22.67 GFLOPS | Progress: (20/20) | 8.03 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.73/ 14.73 GFLOPS | Progress: (4/20) | 3.91 s
[Task 3/25] Current/Best: 23.98/ 23.98 GFLOPS | Progress: (8/20) | 5.48 s
[Task 3/25] Current/Best: 12.58/ 23.98 GFLOPS | Progress: (12/20) | 7.54 s
[Task 3/25] Current/Best: 6.17/ 23.98 GFLOPS | Progress: (16/20) | 9.53 s
[Task 3/25] Current/Best: 16.37/ 23.98 GFLOPS | Progress: (20/20) | 11.48 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 12.06/ 13.87 GFLOPS | Progress: (4/20) | 3.92 s
[Task 4/25] Current/Best: 15.04/ 22.48 GFLOPS | Progress: (8/20) | 5.31 s
[Task 4/25] Current/Best: 9.76/ 22.48 GFLOPS | Progress: (12/20) | 6.96 s
[Task 4/25] Current/Best: 21.42/ 22.48 GFLOPS | Progress: (16/20) | 8.77 s
[Task 4/25] Current/Best: 18.81/ 22.48 GFLOPS | Progress: (20/20) | 13.65 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 13.14/ 13.14 GFLOPS | Progress: (4/20) | 3.29 s
[Task 5/25] Current/Best: 13.48/ 15.01 GFLOPS | Progress: (8/20) | 5.10 s
[Task 5/25] Current/Best: 8.39/ 17.15 GFLOPS | Progress: (12/20) | 7.20 s
[Task 5/25] Current/Best: 9.74/ 17.15 GFLOPS | Progress: (16/20) | 9.57 s
[Task 5/25] Current/Best: 13.37/ 17.15 GFLOPS | Progress: (20/20) | 11.52 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 15.76/ 15.76 GFLOPS | Progress: (4/20) | 5.09 s
[Task 6/25] Current/Best: 16.57/ 16.57 GFLOPS | Progress: (8/20) | 7.51 s
[Task 6/25] Current/Best: 11.83/ 16.57 GFLOPS | Progress: (12/20) | 9.44 s
[Task 6/25] Current/Best: 14.53/ 16.57 GFLOPS | Progress: (16/20) | 12.12 s
[Task 6/25] Current/Best: 13.67/ 16.57 GFLOPS | Progress: (20/20) | 14.69 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 14.55/ 14.55 GFLOPS | Progress: (4/20) | 3.69 s
[Task 7/25] Current/Best: 18.33/ 18.33 GFLOPS | Progress: (8/20) | 5.69 s
[Task 7/25] Current/Best: 10.15/ 19.33 GFLOPS | Progress: (12/20) | 7.76 s
[Task 7/25] Current/Best: 16.76/ 19.33 GFLOPS | Progress: (16/20) | 10.56 s
[Task 7/25] Current/Best: 8.06/ 19.33 GFLOPS | Progress: (20/20) | 13.82 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.41/ 14.02 GFLOPS | Progress: (4/20) | 13.64 s
[Task 8/25] Current/Best: 6.81/ 17.39 GFLOPS | Progress: (8/20) | 16.40 s
[Task 8/25] Current/Best: 12.27/ 17.39 GFLOPS | Progress: (12/20) | 28.09 s
[Task 8/25] Current/Best: 8.38/ 17.39 GFLOPS | Progress: (16/20) | 30.65 s
[Task 8/25] Current/Best: 21.76/ 21.76 GFLOPS | Progress: (20/20) | 32.93 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 8.24/ 10.13 GFLOPS | Progress: (4/20) | 5.14 s
[Task 9/25] Current/Best: 17.31/ 17.31 GFLOPS | Progress: (8/20) | 8.94 s
[Task 9/25] Current/Best: 19.85/ 19.85 GFLOPS | Progress: (12/20) | 13.74 s
[Task 9/25] Current/Best: 18.91/ 19.85 GFLOPS | Progress: (16/20) | 17.67 s
[Task 9/25] Current/Best: 11.52/ 19.85 GFLOPS | Progress: (20/
20) | 19.87 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 10.23/ 19.06 GFLOPS | Progress: (4/20) | 3.13 s
[Task 10/25] Current/Best: 17.85/ 19.06 GFLOPS | Progress: (8/20) | 4.60 s
[Task 10/25] Current/Best: 10.66/ 19.06 GFLOPS | Progress: (12/20) | 6.38 s
[Task 10/25] Current/Best: 3.82/ 19.06 GFLOPS | Progress: (16/20) | 8.05 s
[Task 10/25] Current/Best: 10.08/ 19.06 GFLOPS | Progress: (20/20) | 11.79 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.89/ 11.41 GFLOPS | Progress: (4/20) | 4.66 s
[Task 11/25] Current/Best: 15.95/ 19.41 GFLOPS | Progress: (8/20) | 6.71 s
[Task 11/25] Current/Best: 15.55/ 19.41 GFLOPS | Progress: (12/20) | 9.40 s
[Task 11/25] Current/Best: 13.04/ 19.41 GFLOPS | Progress: (16/20) | 11.60 s
[Task 11/25] Current/Best: 17.69/ 21.24 GFLOPS | Progress: (20/20) | 13.53 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 18.59/ 21.28 GFLOPS | Progress: (4/20) | 3.15 s
[Task 12/25] Current/Best: 21.53/ 21.53 GFLOPS | Progress: (8/20) | 5.11 s
[Task 12/25] Current/Best: 10.03/ 21.53 GFLOPS | Progress: (12/20) | 7.35 s
[Task 12/25] Current/Best: 7.09/ 21.53 GFLOPS | Progress: (16/20) | 9.58 s
[Task 12/25] Current/Best: 8.17/ 21.53 GFLOPS | Progress: (20/20) | 14.22 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 23.51/ 23.51 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 13.84/ 23.51 GFLOPS | Progress: (8/20) | 5.74 s
[Task 13/25] Current/Best: 11.76/ 23.51 GFLOPS | Progress: (12/20) | 8.56 s
[Task 13/25] Current/Best: 12.83/ 23.51 GFLOPS | Progress: (16/20) | 10.35 s
[Task 13/25] Current/Best: 5.76/ 23.51 GFLOPS | Progress: (20/20) | 12.61 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 15.67/ 15.67 GFLOPS | Progress: (4/20) | 3.43 s
[Task 14/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (8/20) | 6.38 s
[Task 14/25] Current/Best: 13.52/ 19.58 GFLOPS | Progress: (12/20) | 11.28 s
[Task 14/25] Current/Best: 6.06/ 19.58 GFLOPS | Progress: (16/20) | 14.33 s
[Task 14/25] Current/Best: 10.37/ 19.58 GFLOPS | Progress: (20/20) | 16.30 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 6.86/ 18.04 GFLOPS | Progress: (4/20) | 2.94 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.75/ 19.42 GFLOPS | Progress: (4/20) | 7.82 s
[Task 1/25] Current/Best: 23.65/ 23.65 GFLOPS | Progress: (8/20) | 11.06 s
[Task 1/25] Current/Best: 17.85/ 23.65 GFLOPS | Progress: (12/20) | 13.43 s
[Task 1/25] Current/Best: 13.52/ 23.65 GFLOPS | Progress: (16/20) | 16.13 s
[Task 1/25] Current/Best: 12.43/ 23.65 GFLOPS | Progress: (20/20) | 21.61 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 8.03/ 21.41 GFLOPS | Progress: (4/20) | 2.52 s
[Task 2/25] Current/Best: 14.39/ 21.41 GFLOPS | Progress: (8/20) | 3.59 s
[Task 2/25] Current/Best: 15.81/ 23.06 GFLOPS | Progress: (12/20) | 4.86 s
[Task 2/25] Current/Best: 12.58/ 23.06 GFLOPS | Progress: (16/20) | 6.33 s
[Task 2/25] Current/Best: 8.29/ 23.06 GFLOPS | Progress: (20/20) | 8.30 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 6.77/ 23.89 GFLOPS | Progress: (4/20) | 3.45 s
[Task 3/25] Current/Best: 19.40/ 23.89 GFLOPS | Progress: (8/20) | 5.31 s
[Task 3/25] Current/Best: 15.54/ 23.89 GFLOPS | Progress: (12/20) | 7.27 s
[Task 3/25] Current/Best: 5.61/ 23.89 GFLOPS | Progress: (16/20) | 10.66 s
[Task 3/25] Current/Best: 5.28/ 23.89 GFLOPS | Progress: (20/20) | 14.99 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.40/ 18.76 GFLOPS | Progress: (4/20) | 3.05 s
[Task 4/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (8/20) | 6.99 s
[Task 4/25] Current/Best: 6.19/ 19.99 GFLOPS | Progress: (12/20) | 12.20 s
[Task 4/25] Current/Best: 16.57/ 20.19 GFLOPS | Progress: (16/20) | 18.44 s
[Task 4/25] Current/Best: 12.37/ 20.19 GFLOPS | Progress: (20/20) | 20.20 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 5.63/ 20.55 GFLOPS | Progress: (4/20) | 3.57 s
[Task 5/25] Current/Best: 3.92/ 20.98 GFLOPS | Progress: (8/20) | 5.37 s
[Task 5/25] Current/Best: 15.45/ 20.98 GFLOPS | Progress: (12/20) | 7.13 s
[Task 5/25] Current/Best: 13.93/ 20.98 GFLOPS | Progress: (16/20) | 9.19 s
[Task 5/25] Current/Best: 12.76/ 20.98 GFLOPS | Progress: (20/20) | 12.68 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 18.87/ 18.87 GFLOPS | Progress: (4/20) | 3.94 s
[Task 6/25] Current/Best: 7.03/ 18.87 GFLOPS | Progress: (8/20) | 6.44 s
[Task 6/25] Current/Best: 11.09/ 18.87 GFLOPS | Progress: (12/20) | 10.86 s
[Task 6/25] Current/Best: 13.13/ 18.87 GFLOPS | Progress: (16/20) | 13.36 s
[Task 6/25] Current/Best: 14.36/ 18.87 GFLOPS | Progress: (20/20) | 15.44 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 4.90/ 11.86 GFLOPS | Progress: (4/20) | 3.81 s
[Task 7/25] Current/Best: 17.84/ 18.32 GFLOPS | Progress: (8/20) | 7.05 s
[Task 7/25] Current/Best: 6.30/ 18.32 GFLOPS | Progress: (12/20) | 9.72 s
[Task 7/25] Current/Best: 11.72/ 18.32 GFLOPS | Progress: (16/20) | 12.15 s
[Task 7/25] Current/Best: 18.74/ 19.94 GFLOPS | Progress: (20/20) | 14.17 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.38/ 21.12 GFLOPS | Progress: (4/20) | 4.69 s
[Task 8/25] Current/Best: 6.45/ 21.12 GFLOPS | Progress: (8/20) | 6.85 s
[Task 8/25] Current/Best: 13.36/ 21.12 GFLOPS | Progress: (12/20) | 18.12 s
[Task 8/25] Current/Best: 9.88/ 21.12 GFLOPS | Progress: (16/20) | 21.36 s
[Task 8/25] Current/Best: 9.35/ 21.12 GFLOPS | Progress: (20/20) | 30.59 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 16.46/ 16.46 GFLOPS | Progress: (4/20) | 2.94 s
[Task 9/25] Current/Best: 8.15/ 19.55 GFLOPS | Progress: (8/20) | 6.51 s
[Task 9/25] Current/Best: 17.08/ 19.55 GFLOPS | Progress: (12/20) | 8.01 s
[Task 9/25] Current/Best: 18.65/ 19.55 GFLOPS | Progress: (16/20) | 9.62 s
[Task 9/25] Current/Best: 6.10/ 22.73 GFLOPS | Progress: (20/20)
| 18.32 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 9.32/ 13.81 GFLOPS | Progress: (4/20) | 3.77 s
[Task 10/25] Current/Best: 6.84/ 15.59 GFLOPS | Progress: (8/20) | 5.17 s
[Task 10/25] Current/Best: 18.06/ 20.05 GFLOPS | Progress: (12/20) | 6.53 s
[Task 10/25] Current/Best: 3.03/ 20.05 GFLOPS | Progress: (16/20) | 10.53 s
[Task 10/25] Current/Best: 10.54/ 20.05 GFLOPS | Progress: (20/20) | 12.47 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.93/ 12.31 GFLOPS | Progress: (4/20) | 4.06 s
[Task 11/25] Current/Best: 19.26/ 23.28 GFLOPS | Progress: (8/20) | 6.13 s
[Task 11/25] Current/Best: 1.59/ 23.28 GFLOPS | Progress: (12/20) | 9.87 s
[Task 11/25] Current/Best: 22.20/ 23.28 GFLOPS | Progress: (16/20) | 11.89 s
[Task 11/25] Current/Best: 15.61/ 23.28 GFLOPS | Progress: (20/20) | 14.15 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 17.00/ 21.91 GFLOPS | Progress: (4/20) | 4.50 s
[Task 12/25] Current/Best: 5.47/ 21.91 GFLOPS | Progress: (8/20) | 6.91 s
[Task 12/25] Current/Best: 11.95/ 21.91 GFLOPS | Progress: (12/20) | 9.05 s
[Task 12/25] Current/Best: 10.42/ 21.91 GFLOPS | Progress: (16/20) | 15.33 s
[Task 12/25] Current/Best: 12.57/ 21.91 GFLOPS | Progress: (20/20) | 18.37 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 20.60/ 20.60 GFLOPS | Progress: (4/20) | 4.41 s
[Task 13/25] Current/Best: 18.65/ 20.60 GFLOPS | Progress: (8/20) | 7.04 s
[Task 13/25] Current/Best: 3.11/ 20.60 GFLOPS | Progress: (12/20) | 10.36 s
[Task 13/25] Current/Best: 1.57/ 20.60 GFLOPS | Progress: (16/20) | 15.42 s
[Task 13/25] Current/Best: 13.28/ 20.60 GFLOPS | Progress: (20/20) | 17.50 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.51/ 14.68 GFLOPS | Progress: (4/20) | 3.57 s
[Task 14/25] Current/Best: 10.79/ 16.27 GFLOPS | Progress: (8/20) | 7.87 s Done.
+
[Task 14/25] Current/Best: 10.90/ 17.41 GFLOPS | Progress: (12/20) | 9.87 s
[Task 14/25] Current/Best: 10.68/ 17.41 GFLOPS | Progress: (16/20) | 14.37 s
[Task 14/25] Current/Best: 16.08/ 17.41 GFLOPS | Progress: (20/20) | 16.50 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 21.57/ 21.57 GFLOPS | Progress: (4/20) | 3.82 s
[Task 15/25] Current/Best: 18.31/ 21.57 GFLOPS | Progress: (8/20) | 8.81 s
[Task 15/25] Current/Best: 18.78/ 21.57 GFLOPS | Progress: (12/20) | 10.44 s
[Task 15/25] Current/Best: 15.31/ 21.57 GFLOPS | Progress: (16/20) | 13.03 s
[Task 15/25] Current/Best: 9.49/ 21.57 GFLOPS | Progress: (20/20) | 18.99 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 12.30/ 17.84 GFLOPS | Progress: (4/20) | 2.94 s
[Task 16/25] Current/Best: 14.71/ 17.84 GFLOPS | Progress: (8/20
) | 4.33 s Done.
+
[Task 16/25] Current/Best: 6.85/ 18.56 GFLOPS | Progress: (12/20) | 5.73 s
[Task 16/25] Current/Best: 11.64/ 19.06 GFLOPS | Progress: (16/20) | 6.93 s
[Task 16/25] Current/Best: 2.80/ 19.06 GFLOPS | Progress: (20/20) | 9.84 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.03/ 20.50 GFLOPS | Progress: (4/20) | 3.52 s
[Task 17/25] Current/Best: 8.99/ 20.50 GFLOPS | Progress: (8/20) | 8.04 s
[Task 17/25] Current/Best: 10.01/ 20.50 GFLOPS | Progress: (12/20) | 10.34 s
[Task 17/25] Current/Best: 16.23/ 21.30 GFLOPS | Progress: (16/20) | 13.78 s
[Task 17/25] Current/Best: 16.46/ 21.30 GFLOPS | Progress: (20/20) | 17.34 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.59/ 20.41 GFLOPS | Progress: (4/20) | 3.44 s
[Task 18/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (8/20) | 5.25 s
[Task 18/25] Current/Best: 12.37/ 20.86 GFLOPS | Progress: (12/20) | 10.84 s
[Task 18/25] Current/Best: 11.36/ 20.86 GFLOPS | Progress: (16/20) | 13.90 s
[Task 18/25] Current/Best: 18.15/ 20.86 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: 10.94/ 23.09 GFLOPS | Progress: (4/20) | 6.07 s
[Task 19/25] Current/Best: 11.17/ 23.09 GFLOPS | Progress: (8/20) | 11.90 s
[Task 19/25] Current/Best: 3.09/ 23.09 GFLOPS | Progress: (12/20) | 16.65 s
[Task 19/25] Current/Best: 19.30/ 23.09 GFLOPS | Progress: (16/20) | 18.87 s
[Task 19/25] Current/Best: 17.88/ 23.09 GFLOPS | Progress: (20/20) | 21.58 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.56/ 13.09 GFLOPS | Progress: (4/20) | 3.70 s
[Task 20/25] Current/Best: 5.21/ 18.07 GFLOPS | Progress: (8/20) | 7.52 s
[Task 20/25] Current/Best: 11.68/ 18.07 GFLOPS | Progress: (12/20) | 9.33 s
[Task 20/25] Current/Best: 14.19/ 21.56 GFLOPS | Progress: (16/20) | 11.76 s
[Task 20/25] Current/Best: 7.37/ 21.56 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: 6.38/ 19.16 GFLOPS | Progress: (4/20) | 3.11 s
[Task 21/25] Current/Best: 20.35/ 20.35 GFLOPS | Progress: (8/20) | 6.91 s
[Task 21/25] Current/Best: 11.27/ 20.35 GFLOPS | Progress: (12/20) | 9.17 s
[Task 21/25] Current/Best: 15.94/ 22.10 GFLOPS | Progress: (16/20) | 11.31 s
[Task 21/25] Current/Best: 14.08/ 22.10 GFLOPS | Progress: (20/20)
| 12.67 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 13.06/ 13.06 GFLOPS | Progress: (4/20) | 3.97 s
[Task 22/25] Current/Best: 10.64/ 20.54 GFLOPS | Progress: (8/20) | 5.72 s Done.
Done.
-
[Task 15/25] Current/Best: 19.11/ 20.16 GFLOPS | Progress: (8/20) | 4.28 s
[Task 15/25] Current/Best: 10.53/ 20.16 GFLOPS | Progress: (12/20) | 9.33 s
[Task 15/25] Current/Best: 13.04/ 22.15 GFLOPS | Progress: (16/20) | 10.81 s
[Task 15/25] Current/Best: 16.38/ 22.15 GFLOPS | Progress: (20/20) | 12.31 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 11.21/ 20.70 GFLOPS | Progress: (4/20) | 3.90 s
[Task 16/25] Current/Best: 13.35/ 20.70 GFLOPS | Progress: (8/20) | 6.72 s
[Task 16/25] Current/Best: 13.69/ 20.70 GFLOPS | Progress: (12/20) | 8.38 s
[Task 16/25] Current/Best: 14.93/ 20.70 GFLOPS | Progress: (16/20) | 10.03 s
[Task 16/25] Current/Best: 13.40/ 20.70 GFLOPS | Progress: (20/20) | 11.34 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 9.31/ 20.44 GFLOPS | Progress: (4/20) | 4.00 s
[Task 17/25] Current/Best: 5.35/ 20.44 GFLOPS | Progress: (8/20) | 6.42 s
[Task 17/25] Current/Best: 16.04/ 20.44 GFLOPS | Progress: (12/20) | 9.84 s
[Task 17/25] Current/Best: 14.82/ 21.93 GFLOPS | Progress: (16/20) | 13.13 s
[Task 17/25] Current/Best: 16.75/ 21.93 GFLOPS | Progress: (20/20) | 16.18 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 14.83/ 18.19 GFLOPS | Progress: (4/20) | 3.25 s
[Task 18/25] Current/Best: 11.40/ 18.27 GFLOPS | Progress: (8/20) | 5.39 s
[Task 18/25] Current/Best: 11.83/ 19.55 GFLOPS | Progress: (12/20) | 7.44 s
[Task 18/25] Current/Best: 10.25/ 19.55 GFLOPS | Progress: (16/20) | 11.23 s
[Task 18/25] Current/Best: 14.98/ 19.55 GFLOPS | Progress: (20/20) | 14.63 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 12.05/ 18.99 GFLOPS | Progress: (4/20) | 4.62 s
[Task 19/25] Current/Best: 19.00/ 21.84 GFLOPS | Progress: (8/20) | 6.66 s
[Task 19/25] Current/Best: 10.30/ 21.84 GFLOPS | Progress: (12/20) | 10.46 s
[Task 19/25] Current/Best: 8.99/ 21.84 GFLOPS | Progress: (16/20) | 13.86 s
[Task 19/25] Current/Best: 18.17/ 21.84 GFLOPS | Progress: (20/20) | 16.46 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.74/ 12.50 GFLOPS | Progress: (4/20) | 3.38 s
[Task 20/25] Current/Best: 9.22/ 17.91 GFLOPS | Progress: (8/20) | 6.32 s
[Task 20/25] Current/Best: 16.64/ 17.91 GFLOPS | Progress: (12/20) | 9.46 s
[Task 20/25] Current/Best: 10.19/ 17.91 GFLOPS | Progress: (16/20) | 11.34 s
[Task 20/25] Current/Best: 17.38/ 17.91 GFLOPS | Progress: (20/20) | 14.51 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 21/25] Current/Best: 13.54/ 13.54 GFLOPS | Progress: (4/20) | 3.01 s
[Task 21/25] Current/Best: 5.35/ 15.15 GFLOPS | Progress: (8/20) | 5.29 s
[Task 21/25] Current/Best: 16.33/ 16.33 GFLOPS | Progress: (12/20) | 7.36 s
[Task 21/25] Current/Best: 10.31/ 20.17 GFLOPS | Progress: (16/20) | 9.32 s
[Task 21/25] Current/Best: 9.47/ 20.17 GFLOPS | Progress: (20/20) | 11.79 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.75/ 15.75 GFLOPS | Progress: (4/20) | 3.52 s
[Task 22/25] Current/Best: 13.60/ 15.75 GFLOPS | Progress: (8/20) | 5.78 s
[Task 22/25] Current/Best: 12.22/ 21.68 GFLOPS | Progress: (12/20) | 7.21 s
[Task 22/25] Current/Best: 13.78/ 21.68 GFLOPS | Progress: (16/20) | 8.87 s
[Task 22/25] Current/Best: 4.09/ 21.68 GFLOPS | Progress: (20/20) | 10.82 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.16/ 18.39 GFLOPS | Progress: (4/20) | 5.81 s
[Task 23/25] Current/Best: 17.80/ 22.51 GFLOPS | Progress: (8/20) | 7.90 s
[Task 23/25] Current/Best: 12.43/ 22.79 GFLOPS | Progress: (12/20) | 11.19 s
[Task 23/25] Current/Best: 12.77/ 22.79 GFLOPS | Progress: (16/20) | 14.36 s
[Task 23/25] Current/Best: 12.25/ 22.79 GFLOPS | Progress: (20/20) | 17.54 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.69/ 3.69 GFLOPS | Progress: (4/20) | 12.27 s
[Task 24/25] Current/Best: 9.77/ 9.77 GFLOPS | Progress: (8/20) | 22.75 s
[Task 24/25] Current/Best: 2.28/ 10.04 GFLOPS | Progress: (12/20) | 29.02 s
[Task 24/25] Current/Best: 7.51/ 10.60 GFLOPS | Progress: (16/20) | 39.48 s
[Task 24/25] Current/Best: 0.78/ 10.60 GFLOPS | Progress: (20/20) | 51.38 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 4.12/ 9.33 GFLOPS | Progress: (4/20) | 12.22 s
[Task 25/25] Current/Best: 6.00/ 9.33 GFLOPS | Progress: (8/20) | 22.97 s
[Task 25/25] Current/Best: 3.01/ 9.33 GFLOPS | Progress: (12/20) | 34.45 s
[Task 25/25] Current/Best: 5.39/ 9.33 GFLOPS | Progress: (16/20) | 41.84 s
[Task 25/25] Current/Best: 5.23/ 9.33 GFLOPS | Progress: (2
0/20) | 52.35 s
+
[Task 22/25] Current/Best: 14.00/ 20.54 GFLOPS | Progress: (12/20) | 8.01 s
[Task 22/25] Current/Best: 10.78/ 20.54 GFLOPS | Progress: (16/20) | 10.76 s
[Task 22/25] Current/Best: 5.26/ 20.54 GFLOPS | Progress: (20/20) | 13.11 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 19.41/ 19.41 GFLOPS | Progress: (4/20) | 10.20 s
[Task 23/25] Current/Best: 10.62/ 19.41 GFLOPS | Progress: (8/20) | 12.24 s
[Task 23/25] Current/Best: 17.91/ 19.41 GFLOPS | Progress: (12/20) | 14.62 s
[Task 23/25] Current/Best: 21.94/ 21.94 GFLOPS | Progress: (16/20) | 18.00 s
[Task 23/25] Current/Best: 7.43/ 21.94 GFLOPS | Progress: (20/20) | 21.77 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.46/ 6.86 GFLOPS | Progress: (4/20) | 12.08 s
[Task 24/25] Current/Best: 3.30/ 8.63 GFLOPS | Progress: (8/20) | 14.97 s
[Task 24/25] Current/Best: 2.02/ 10.64 GFLOPS | Progress: (12/20) | 17.59 s
[Task 24/25] Current/Best: 3.37/ 10.64 GFLOPS | Progress: (16/20) | 28.31 s
[Task 24/25] Current/Best: 3.57/ 10.64 GFLOPS | Progress: (20/20) | 38.84 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 5.79 GFLOPS | Progress: (4/20) | 3.53 s Done.
+
[Task 25/25] Current/Best: 8.48/ 8.48 GFLOPS | Progress: (8/20) | 14.01 s
[Task 25/25] Current/Best: 1.55/ 8.48 GFLOPS | Progress: (12/20) | 16.15 s
[Task 25/25] Current/Best: 9.04/ 9.04 GFLOPS | Progress: (16/20) | 26.64 s
[Task 25/25] Current/Best: 5.31/ 9.04 GFLOPS | Progress: (20/20) | 38.16 s
@@ -672,8 +673,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621103
+ 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
@@ -730,8 +731,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 415.02006364999716, 'median': 415.1313719999962, 'std': 2.8967793135913644}
- unoptimized: {'mean': 516.4690437500008, 'median': 516.2654152999949, 'std': 1.9471380053512977}
+ optimized: {'mean': 414.4846720199962, 'median': 414.8631147499941, 'std': 1.3101257155342834}
+ unoptimized: {'mean': 523.8234768699988, 'median': 524.8220038499994, 'std': 3.2826715339377572}
@@ -754,7 +755,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 52.204 seconds)
+ **Total running time of the script:** ( 11 minutes 12.873 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 b01c15dab6..759040654d 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
- 1.432e-07 secs/op
+ 1.228e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 74ef2e9257..c5f1a12fef 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, 0x14680220)), stage(b, placeholder(b, 0xcd3bd10)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x20e50ad0)), stage(b, placeholder(b, 0xbe70680)), 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 e7e5669c5e..2e1bec66fa 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
=================
-**14:36.533** total execution time for **tutorial** files:
+**14:34.315** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:52.204 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:12.873 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:33.374 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:12.380 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.470 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.674 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.180 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.389 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:32.369 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:30.026 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.980 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.015 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.771 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.775 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.173 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.174 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 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_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index a8e1f17d06..fdd7240092 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,8 +294,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
- naive: 0.000009
+ Numpy running time: 0.000008
+ naive: 0.000007
@@ -449,7 +449,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000026
+ vector: 0.000025
@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, [(stride: int32*n: int32)], [], type="auto"),
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.452039999407134e-06 1.0
- naive 8.7556e-06 1.174926597374219
- parallel 6.994999999999999e-06 0.9386691430207708
- vector 2.6487500000000003e-05 3.5543958435686447
+ numpy 8.008879999579222e-06 1.0
+ naive 7.0584999999999986e-06 0.8813342190631954
+ parallel 7.245e-06 0.9046208708809028
+ vector 2.46111e-05 3.0729764962507917
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018794
+ Numpy running time: 0.019354
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.350327
+ none: 3.352561
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.305137
+ blocking: 0.310994
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.343320
+ vectorization: 0.348775
@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: 0.115940
+ loop permutation: 0.117330
@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: 0.108659
+ array packing: 0.108827
@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: 0.110566
+ block caching: 0.114451
@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: 0.146814
+ parallelization: 0.152127
@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 3.350326625 1.0
- blocking 0.3051367483 0.09107671652760124
- vectorization 0.34331965799999997 0.10247348883483859
- loop permutation 0.11594009779999999 0.03460561037089928
- array packing 0.10865868009999999 0.03243226474970929
- block caching 0.11056552580000001 0.0330014169290136
- parallelization 0.14681377 0.043820733448638016
+ none 3.3525605522 1.0
+ blocking 0.3109940758 0.09276314952638844
+ vectorization 0.3487747141 0.10403233846772099
+ loop permutation 0.11732950679999998 0.03499698364075978
+ array packing 0.10882732669999999 0.032460957827767166
+ block caching 0.11445055850000001 0.03413825245449955
+ parallelization 0.15212737469999998 0.045376473394394545
@@ -1663,7 +1663,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.470 seconds)
+ **Total running time of the script:** ( 1 minutes 0.674 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 8d0240ca79..e412884854 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-e43841d2efec6eedaace0c9a53cd63c607b93c36
+be30238947305ccbf63655fb11162e726c319804
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index f108cfeae3..79a3617ba6 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 9.144 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.989 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 4763964f8a..2f9aaefe14 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 963ms/step
+1/1 [==============================] - 1s 971ms/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 ce808c6166..1c929c1b14 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.zipac2632f8-a4b0-46fa-ba95-f4230d4f741c 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.zip3a337837-a906-4c42-9ccc-15983d4ed30b 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 182d5e24ff..669f1714f8 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,10 +448,9 @@ 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]
- 25%|##4 | 10.3M/41.5M [00:00<00:00, 107MB/s]
- 49%|####9 | 20.5M/41.5M [00:00<00:00, 107MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 109MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 121MB/s]
+ 30%|##9 | 12.3M/41.5M [00:00<00:00, 129MB/s]
+ 59%|#####9 | 24.6M/41.5M [00:00<00:00, 78.5MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 107MB/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 cd29e35881..174fc88aa5 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,10 +431,10 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 31%|### | 13.7M/44.7M [00:00<00:00, 144MB/s]
- 61%|######1 | 27.5M/44.7M [00:00<00:00, 115MB/s]
- 87%|########6 | 38.7M/44.7M [00:00<00:00, 108MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 110MB/s]
+ 28%|##7 | 12.3M/44.7M [00:00<00:00, 129MB/s]
+ 55%|#####5 | 24.6M/44.7M [00:00<00:00, 110MB/s]
+ 79%|#######8 | 35.2M/44.7M [00:00<00:00, 106MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 107MB/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 2a4975bff6..b1f6080c9f 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 11.266 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.697 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 a8972b515a..9d939231c3 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>05:42.569</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:40.740</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:11.266</p></td>
+<td><p>01:10.697</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:09.144</p></td>
+<td><p>01:06.989</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:46.834</p></td>
+<td><p>00:45.623</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>00:32.174</p></td>
+<td><p>00:31.963</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:30.563</p></td>
+<td><p>00:30.778</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>00:26.227</p></td>
+<td><p>00:27.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.467</p></td>
+<td><p>00:24.651</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>00:21.754</p></td>
+<td><p>00:21.905</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:17.777</p></td>
+<td><p>00:18.726</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>00:02.363</p></td>
+<td><p>00:02.382</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 cf30fd9cec..0d93ddb371 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)
- 17.3620 16.1833 23.2615 15.7846 2.2554
+ 16.4628 16.6644 17.0116 15.8147 0.4126
</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 d54fc1a97c..e88137795b 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,23 +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]
- 7%|6 | 11.9M/170M [00:00<00:01, 125MB/s]
- 14%|#3 | 23.8M/170M [00:00<00:01, 109MB/s]
- 20%|## | 34.3M/170M [00:00<00:01, 105MB/s]
- 26%|##6 | 44.3M/170M [00:00<00:01, 103MB/s]
- 32%|###1 | 54.2M/170M [00:00<00:01, 102MB/s]
- 38%|###7 | 63.9M/170M [00:00<00:01, 101MB/s]
- 43%|####3 | 73.6M/170M [00:00<00:01, 101MB/s]
- 49%|####9 | 83.2M/170M [00:00<00:00, 101MB/s]
- 55%|#####4 | 92.9M/170M [00:00<00:00, 100MB/s]
- 60%|###### | 102M/170M [00:01<00:00, 100MB/s]
- 66%|######5 | 112M/170M [00:01<00:00, 98.6MB/s]
- 72%|#######1 | 122M/170M [00:01<00:00, 101MB/s]
- 78%|#######7 | 132M/170M [00:01<00:00, 101MB/s]
- 83%|########3 | 141M/170M [00:01<00:00, 100MB/s]
- 89%|########8 | 151M/170M [00:01<00:00, 100MB/s]
- 94%|#########4| 160M/170M [00:01<00:00, 99.4MB/s]
-100%|##########| 170M/170M [00:01<00:00, 101MB/s]
+ 8%|7 | 12.8M/170M [00:00<00:01, 134MB/s]
+ 15%|#5 | 25.6M/170M [00:00<00:01, 112MB/s]
+ 21%|##1 | 36.5M/170M [00:00<00:01, 107MB/s]
+ 28%|##7 | 46.8M/170M [00:00<00:01, 104MB/s]
+ 33%|###3 | 56.8M/170M [00:00<00:01, 95.2MB/s]
+ 40%|#### | 68.7M/170M [00:00<00:01, 104MB/s]
+ 46%|####6 | 78.8M/170M [00:00<00:00, 103MB/s]
+ 52%|#####2 | 88.7M/170M [00:00<00:00, 102MB/s]
+ 58%|#####7 | 98.5M/170M [00:00<00:00, 101MB/s]
+ 64%|######3 | 108M/170M [00:01<00:00, 101MB/s]
+ 69%|######9 | 118M/170M [00:01<00:00, 101MB/s]
+ 75%|#######5 | 127M/170M [00:01<00:00, 100MB/s]
+ 81%|######## | 137M/170M [00:01<00:00, 100MB/s]
+ 86%|########6 | 147M/170M [00:01<00:00, 100MB/s]
+ 92%|#########1| 156M/170M [00:01<00:00, 100MB/s]
+ 98%|#########7| 166M/170M [00:01<00:00, 100MB/s]
+100%|##########| 170M/170M [00:01<00:00, 102MB/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=& [...]
@@ -567,7 +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 19.523 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 14.858 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 c7b0945604..724beba9fb 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -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)
- 90.3967 90.2581 94.7032 90.0214 0.5918
+ 90.5660 90.2833 101.4373 90.0897 1.2687
</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 5.853 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.665 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 fe04552300..69cea3aeff 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.3716 121.3126 124.8323 120.6581 0.4649
+ 121.8195 121.7278 127.9332 121.0439 0.7270
</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 23.806 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 23.053 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 441c4a0e3a..07e65d0cef 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 13.738 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.265 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 99c194ca59..2a88528d6d 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,23 +462,22 @@ 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]
- 5%|5 | 6655/132723 [00:00<00:01, 66545.78KB/s]
- 11%|#1 | 14614/132723 [00:00<00:01, 74196.11KB/s]
- 17%|#7 | 22632/132723 [00:00<00:01, 76926.60KB/s]
- 23%|##3 | 30612/132723 [00:00<00:01, 78057.94KB/s]
- 29%|##9 | 38541/132723 [00:00<00:01, 78501.00KB/s]
- 35%|###5 | 46511/132723 [00:00<00:01, 78905.33KB/s]
- 41%|####1 | 54524/132723 [00:00<00:00, 79303.41KB/s]
- 47%|####7 | 62574/132723 [00:00<00:00, 79681.74KB/s]
- 53%|#####3 | 70593/132723 [00:00<00:00, 79838.86KB/s]
- 59%|#####9 | 78697/132723 [00:01<00:00, 80199.29KB/s]
- 65%|######5 | 86761/132723 [00:01<00:00, 80323.98KB/s]
- 71%|#######1 | 94864/132723 [00:01<00:00, 80534.94KB/s]
- 78%|#######7 | 102918/132723 [00:01<00:00, 80510.92KB/s]
- 84%|########3 | 110985/132723 [00:01<00:00, 80552.89KB/s]
- 90%|########9 | 119041/132723 [00:01<00:00, 79672.50KB/s]
- 96%|#########5| 127011/132723 [00:01<00:00, 79131.08KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 79050.52KB/s]
+ 3%|3 | 4011/132723 [00:00<00:03, 40107.17KB/s]
+ 9%|9 | 12129/132723 [00:00<00:01, 64264.74KB/s]
+ 16%|#5 | 21025/132723 [00:00<00:01, 75525.46KB/s]
+ 23%|##2 | 29965/132723 [00:00<00:01, 80999.55KB/s]
+ 29%|##9 | 38785/132723 [00:00<00:01, 82595.52KB/s]
+ 36%|###5 | 47688/132723 [00:00<00:01, 84756.63KB/s]
+ 43%|####2 | 56538/132723 [00:00<00:00, 85972.02KB/s]
+ 49%|####9 | 65430/132723 [00:00<00:00, 86905.71KB/s]
+ 56%|#####6 | 74371/132723 [00:00<00:00, 87683.98KB/s]
+ 63%|######2 | 83271/132723 [00:01<00:00, 88088.19KB/s]
+ 69%|######9 | 92081/132723 [00:01<00:00, 87848.74KB/s]
+ 76%|#######6 | 100898/132723 [00:01<00:00, 87944.95KB/s]
+ 83%|########2 | 109693/132723 [00:01<00:00, 87524.93KB/s]
+ 89%|########9 | 118447/132723 [00:01<00:00, 87018.68KB/s]
+ 96%|#########5| 127150/132723 [00:01<00:00, 86731.30KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 84210.72KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +516,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 58.324 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 2.922 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 c6a288d81e..09959a631d 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>12:27.573</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:26.487</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:19.523</p></td>
+<td><p>03:14.858</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:58.324</p></td>
+<td><p>03:02.922</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>02:23.806</p></td>
+<td><p>02:23.053</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>01:13.738</p></td>
+<td><p>01:14.265</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>01:05.853</p></td>
+<td><p>01:06.665</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>00:36.593</p></td>
+<td><p>00:35.485</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>00:25.228</p></td>
+<td><p>00:24.869</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>00:24.502</p></td>
+<td><p>00:24.364</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>00:00.007</p></td>
+<td><p>00:00.006</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 c54654dc02..6c7f9c0f7d 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.zipa864aaa3-d1e7-4acb-928a-1c4a408622a7 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.zip6032e6aa-cae1-43fb-9d47-412ec80214e1 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 afda2edd3d..7d129f4d0d 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>00:48.240</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:48.452</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:44.766</p></td>
+<td><p>00:44.959</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>00:02.426</p></td>
+<td><p>00:02.440</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>00:01.041</p></td>
+<td><p>00:01.046</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index b1667d74d6..6292165b26 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: 6912us [6912us] (47.46%; 47.46%)
-FoldScaleAxis: 7653us [5us] (52.54%; 52.54%)
- FoldConstant: 7648us [1559us] (52.51%; 99.93%)
- InferType: 6088us [6088us] (41.80%; 79.61%)
+InferType: 6689us [6689us] (46.46%; 46.46%)
+FoldScaleAxis: 7707us [6us] (53.54%; 53.54%)
+ FoldConstant: 7701us [1528us] (53.50%; 99.93%)
+ InferType: 6173us [6173us] (42.88%; 80.15%)
</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: 6122us [6122us] (44.72%; 44.72%)
-FoldScaleAxis: 7568us [5us] (55.28%; 55.28%)
- FoldConstant: 7564us [1541us] (55.25%; 99.94%)
- InferType: 6023us [6023us] (43.99%; 79.63%)
+InferType: 6139us [6139us] (44.79%; 44.79%)
+FoldScaleAxis: 7567us [5us] (55.21%; 55.21%)
+ FoldConstant: 7563us [1536us] (55.18%; 99.94%)
+ InferType: 6027us [6027us] (43.97%; 79.69%)
</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 065de2d749..a42b72e64b 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: 36.620414 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.050209 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 de043873a4..186d7d2a34 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: 12.418589 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.358694 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 b2d8e851d3..51f2d415b2 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: 0.018290
-Baseline: 3.393212
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019383
+Baseline: 3.343131
</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: 0.302268
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300793
</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: 0.327429
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.333112
</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: 0.118018
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116146
</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: 0.110064
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109314
</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: 0.111293
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.115390
</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: 0.147344
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.152871
</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 794bc4fd7b..6edb5482ad 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>00:34.790</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.186</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.180</p></td>
+<td><p>00:32.515</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>00:01.461</p></td>
+<td><p>00:01.561</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>00:01.149</p></td>
+<td><p>00:01.110</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 bde280c3d9..73445acf47 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>09:04.325</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:07.578</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>05:34.905</p></td>
+<td><p>05:40.928</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:33.231</p></td>
+<td><p>01:32.351</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>01:04.278</p></td>
+<td><p>01:02.894</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>00:28.452</p></td>
+<td><p>00:28.501</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.198</p></td>
+<td><p>00:11.851</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.261</p></td>
+<td><p>00:11.054</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 de34a73e79..b05f966925 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
@@ -504,12 +504,12 @@ 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" = 28;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), 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" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[8] = 0f32
@@ -523,431 +523,380 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 10), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 10), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 9)*7)) + (floormo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 20), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 20), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 9)*7)) + (floor [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 3), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 27), 9)*7)) + (floorm [...]
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[ramp((threadIdx.x_2*3), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 192), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 384), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 576), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 36864), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 768), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 960), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1152), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 73728), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1344), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1536), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1728), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 110592), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 1920), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2112), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2304), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 147456), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2496), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2688), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 2880), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 184320), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3072), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3264), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3456), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 221184), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3648), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 3840), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4032), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 258048), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4224), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4416), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4608), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 294912), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4800), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 4992), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5184), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 331776), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5376), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5568), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5760), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 368640), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 5952), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6144), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6336), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 405504), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6528), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6720), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 6912), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 442368), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7104), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7296), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7488), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 479232), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7680), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 7872), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8064), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 516096), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8256), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8448), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8640), 1, 3)] = kernel[ramp((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 552960), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 8832), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)), 1, 3)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[ramp(((threadIdx.x_2*3) + 9024), 1, 3)] = kernel[ramp(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)), 1, 3)]
- for (rc.outer.inner: int32, 0, 4) {
- let cse_var_56: int32 = (rc.outer.inner*54)
- let cse_var_55: int32 = (cse_var_56 + 9)
- let cse_var_54: int32 = (cse_var_56 + 8)
- let cse_var_53: int32 = (cse_var_56 + 7)
- let cse_var_52: int32 = (cse_var_56 + 6)
- let cse_var_51: int32 = (cse_var_56 + 53)
- let cse_var_50: int32 = (cse_var_56 + 52)
- let cse_var_49: int32 = (cse_var_56 + 51)
- let cse_var_48: int32 = (cse_var_56 + 50)
- let cse_var_47: int32 = (cse_var_56 + 5)
- let cse_var_46: int32 = (cse_var_56 + 49)
- let cse_var_45: int32 = (cse_var_56 + 48)
- let cse_var_44: int32 = (cse_var_56 + 47)
- let cse_var_43: int32 = (cse_var_56 + 46)
- let cse_var_42: int32 = (cse_var_56 + 45)
- let cse_var_41: int32 = (cse_var_56 + 44)
- let cse_var_40: int32 = (cse_var_56 + 43)
- let cse_var_39: int32 = (cse_var_56 + 42)
- let cse_var_38: int32 = (cse_var_56 + 41)
- let cse_var_37: int32 = (cse_var_56 + 40)
- let cse_var_36: int32 = (cse_var_56 + 4)
- let cse_var_35: int32 = (cse_var_56 + 39)
- let cse_var_34: int32 = (cse_var_56 + 38)
- let cse_var_33: int32 = (cse_var_56 + 37)
- let cse_var_32: int32 = (cse_var_56 + 36)
- let cse_var_31: int32 = (cse_var_56 + 35)
- let cse_var_30: int32 = (cse_var_56 + 34)
- let cse_var_29: int32 = (cse_var_56 + 33)
- let cse_var_28: int32 = (cse_var_56 + 32)
- let cse_var_27: int32 = (cse_var_56 + 31)
- let cse_var_26: int32 = (cse_var_56 + 30)
- let cse_var_25: int32 = (cse_var_56 + 3)
- let cse_var_24: int32 = (cse_var_56 + 29)
- let cse_var_23: int32 = (cse_var_56 + 28)
- let cse_var_22: int32 = (cse_var_56 + 27)
- let cse_var_21: int32 = (cse_var_56 + 26)
- let cse_var_20: int32 = (cse_var_56 + 25)
- let cse_var_19: int32 = (cse_var_56 + 24)
- let cse_var_18: int32 = (cse_var_56 + 23)
- let cse_var_17: int32 = (cse_var_56 + 22)
- let cse_var_16: int32 = (cse_var_56 + 21)
- let cse_var_15: int32 = (cse_var_56 + 20)
- let cse_var_14: int32 = (cse_var_56 + 2)
- let cse_var_13: int32 = (cse_var_56 + 19)
- let cse_var_12: int32 = (cse_var_56 + 18)
- let cse_var_11: int32 = (cse_var_56 + 17)
- let cse_var_10: int32 = (cse_var_56 + 16)
- let cse_var_9: int32 = (cse_var_56 + 15)
- let cse_var_8: int32 = (cse_var_56 + 14)
- let cse_var_7: int32 = (cse_var_56 + 13)
- let cse_var_6: int32 = (cse_var_56 + 12)
- let cse_var_5: int32 = (cse_var_56 + 11)
- let cse_var_4: int32 = (cse_var_56 + 10)
- let cse_var_3: int32 = (cse_var_56 + 1)
- {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4608)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4611)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4614)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4617)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4620)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4623)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4609)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4612)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4615)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4618)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4621)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4624)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4610)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4613)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4616)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4619)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4622)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*18)) + 4625)]))
+ for (rc.outer.outer: int32, 0, 16) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_4: int32 = (rc.outer.outer*1568)
+ let cse_var_3: int32 = (rc.outer.outer*288)
+ let cse_var_2: int32 = (ry.outer.outer*7)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*32)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*32), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*32), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormo [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - 8)] [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 2), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 2), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 2), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - 8)] [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 3), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 3), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 3), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - 8)] [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 4)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 4), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - 8)] [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 5)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 5), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 5), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 5), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - 8)] [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 6)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 6), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 6), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 6), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - 8)] [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 7)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 7), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - 8)] [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 8)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 8), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 8), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 8), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - 8)] [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 9)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 1), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 1), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) - 1)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 10)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 10), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 10), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 10), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 11)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 11), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 11), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 11), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 12)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 12), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 12), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 12), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 13)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 13), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 13), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 13), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 14)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 14), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 15)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 15), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 15), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 15), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 16)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 16), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 16), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 16), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 17)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 17), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 17), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 17), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 18)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 2), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 2), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 6)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 19)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 19), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 19), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 19), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 20)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 20), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 20), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 20), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 21)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 21), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 22)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 22), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 22), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 22), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 23)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 23), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 23), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 23), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 24)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 24), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 24), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 24), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 25)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 25), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 25), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 25), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 26)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 26), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 26), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 26), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 27)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 3), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 3), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 13)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*32) + 28)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 28), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 29)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 29), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 29), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 29), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 30)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 30), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 30), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 30), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), 9)) - [...]
+ pad_temp.shared_1[((threadIdx.x_1*32) + 31)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 31), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 31), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 31), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), 9)) - [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1792)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1792), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 1), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1793)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 29), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 29), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1793), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1794)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 30), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 30), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1794), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1795)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 31), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 31), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1795), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1796)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 32), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 32), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1796), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1797)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 33), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 33), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1797), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1798)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 34), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 34), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1798), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1799)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1799), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1800)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 4), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 4), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 1392)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1801)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 1), 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1792), 9)*7)) + cse_var_2) + floormod(((threadId [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1802)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 38), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 38), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1802), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1803)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 39), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 39), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1803), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1804)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 40), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 40), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1804), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1805)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 41), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 41), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1805), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1806)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1806), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1807)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 43), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 43), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1807), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1808)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 44), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 44), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1808), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1809)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 5), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 5), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 1399)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1810)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 2), 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1792), 9)*7)) + cse_var_2) + floormod(((threadId [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1811)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 47), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 47), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1811), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1812)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 48), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 48), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1812), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1813)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1813), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1814)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 50), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 50), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1814), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1815)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 51), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 51), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 6), 9))) && (floormod(((threadIdx.x_1*5) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1815), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 6), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1816)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 52), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 52), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 7), 9))) && (floormod(((threadIdx.x_1*5) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1816), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 7), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1817)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 53), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 53), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 8), 9))) && (floormod(((threadIdx.x_1*5) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1817), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 8), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1818)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 6), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*32), 9) + 6), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*5), 9))) && (floormod((threadIdx.x_1*5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*32), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*5), 9)) + 1406)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1819)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 3), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*32) + 1792), 9) + 3), 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 1), 9))) && (floormod(((threadIdx.x_1*5) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1792), 9)*7)) + cse_var_2) + floormod(((threadId [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1820)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 2), 9))) && (floormod(((threadIdx.x_1*5) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1820), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 2), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1821)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 57), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 57), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 3), 9))) && (floormod(((threadIdx.x_1*5) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1821), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 3), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1822)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 58), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 58), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 4), 9))) && (floormod(((threadIdx.x_1*5) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1822), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 4), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*32) + 1823)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*32) + 59), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*32) + 59), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*5) + 5), 9))) && (floormod(((threadIdx.x_1*5) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*32) + 1823), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*5) + 5), [...]
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 504), 96)*4608)) + cse_var_3) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*73728) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 840), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 952), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 88), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1008), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1064), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 64), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 96)*4608)) + cse_var_3) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1232), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 80), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1288), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*73728) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1400), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1456), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1512), 96)*4608)) + cse_var_3) + ((floordiv(threadIdx.x_2, 3) + 24)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ }
+ for (rc.outer.inner: int32, 0, 8) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 129)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 192)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 130)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 193)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 131)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 194)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 97)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 98)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 101)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 132)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 104)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 195)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*252) + (floormod(threadIdx.x, 7)*9)) + 197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + 107)]))
}
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner) + 3136)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -984,7 +933,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.275 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.334 ms
</pre></div>
</div>
</div>
@@ -1013,33 +962,33 @@ 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=64)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=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=7)
-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_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_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=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)
@@ -1060,14 +1009,14 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
+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=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=32)
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=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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)
@@ -1087,10 +1036,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[216];
- __shared__ float kernel_shared[9216];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -1105,321 +1054,344 @@ extern "C" __global__ void __launch_bounds__(64) default_function_kern
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 < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int) [...]
- pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((in [...]
- if (((int)threadIdx.x) < 24) {
- pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= (((((int)threadIdx.x) + 3) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) + 3) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % [...]
- }
- *(float3*)(kernel_shared + (((int)threadIdx.x) * 3)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 192)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 384)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 576)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 36864));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 768)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 960)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1152)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 73728));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1344)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1536)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1728)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 110592));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 1920)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2112)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2304)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 147456));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2496)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2688)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 2880)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 184320));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3072)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3264)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3456)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 221184));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3648)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 3840)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4032)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 258048));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4224)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4416)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4608)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 294912));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4800)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 4992)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5184)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 331776));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5376)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5568)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5760)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 368640));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 5952)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6144)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6336)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 405504));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6528)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6720)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 6912)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 442368));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7104)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7296)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7488)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 479232));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7680)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 7872)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8064)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 516096));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8256)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8448)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8640)) = *(float3*)(kernel + ((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 552960));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 8832)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)));
- *(float3*)(kernel_shared + ((((int)threadIdx.x) * 3) + 9024)) = *(float3*)(kernel + (((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)));
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rc_outer_inner * 54)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(rc_outer_inner * 54)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 1)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4608)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4611)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4614)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4617)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4620)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4623)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4609)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4612)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4615)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4618)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4621)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4624)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4610)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4613)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4616)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4619)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4622)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 54) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 54) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 54) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 54) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 54) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 54) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 54) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 54) + 53)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 54) + 53)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 18)) + 4625)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 32)] = (((((1 <= ((((((int)threadIdx.x) * 32) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 32) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 2) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 3) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 4) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 4) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 5) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 5) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 5) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 6)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 6) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 6) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 6) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 7) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 8)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 8) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 9)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 1) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 10)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 10) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 10) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 10) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 11)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 11) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 11) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 11) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 12)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 12) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 12) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 12) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 13)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 13) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 13) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 13) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 14)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 14) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 15)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 15) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 16)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 16) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 16) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 17)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 17) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 17) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 17) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 18)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 2) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 2) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 19)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 19) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 19) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 19) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 20)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 20) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 20) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 20) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 21)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 21) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 22)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 22) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 23)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 23) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 23) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 23) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 24)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 24) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 24) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 24) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 25)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 25) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 25) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 25) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 26)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 26) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 26) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 26) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 27)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 3) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 3) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 13)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 28)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 28) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 29)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 29) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 30)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 30) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 31)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 31) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) - 8)] [...]
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1792)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 1) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1793)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1793) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1794)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1794) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1795)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1795) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1796)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 32) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 32) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1796) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1797)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 33) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 33) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1797) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1798)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 34) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 34) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1798) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1799)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1799) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1800)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 1392)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1801)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 1) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1802)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 38) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 38) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1802) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1803)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 39) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 39) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1803) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1804)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 40) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 40) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1804) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1805)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 41) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 41) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1805) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1806)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1806) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1807)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1807) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1808)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 44) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 44) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1808) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1809)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 5) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 1399)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1810)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 2) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 2) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1811)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 47) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 47) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1811) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1812)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 48) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 48) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1812) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1813)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1813) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1814)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1814) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1815)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 51) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 51) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 6) % 9))) && ((((((int)threadIdx.x) * 5) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1815) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 6) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1816)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 52) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 52) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 7) % 9))) && ((((((int)threadIdx.x) * 5) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1816) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 7) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1817)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 53) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 53) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 8) % 9))) && ((((((int)threadIdx.x) * 5) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1817) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 8) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1818)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 6) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 32) / 9) + 6) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 5) % 9))) && (((((int)threadIdx.x) * 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 32) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 5) % 9)) + 1406)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1819)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 3) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 32) + 1792) / 9) + 3) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 1) % 9))) && ((((((int)threadIdx.x) * 5) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1820)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 2) % 9))) && ((((((int)threadIdx.x) * 5) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1820) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 2) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1821)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 3) % 9))) && ((((((int)threadIdx.x) * 5) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1821) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 3) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1822)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 58) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 58) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 4) % 9))) && ((((((int)threadIdx.x) * 5) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1822) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 4) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 7) {
+ pad_temp_shared[((((int)threadIdx.x) * 32) + 1823)] = (((((1 <= (((((((int)threadIdx.x) * 32) + 59) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 32) + 59) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 5) + 5) % 9))) && ((((((int)threadIdx.x) * 5) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 32) + 1823) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 5) + 5) % 9)) [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 216)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 129)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 192)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 130)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 193)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 131)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 194)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12))]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 97)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 98)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 101)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 132)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 104)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 195)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 252) + ((((int)threadIdx.x) % 7) * 9)) + 197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + 107)]));
+ }
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner) + 3136)] = max((conv2d_nchw[(i3_inner + 7)] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -1456,7 +1428,7 @@ 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 34.905 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 40.928 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 1ba0ea0298..31f11c1a55 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)
- 8.2064 8.2100 8.2109 8.1983 0.0057
+ 8.1756 8.1743 8.1839 8.1687 0.0063
</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 4.278 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.894 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 66d8a97344..9d7b5bf47c 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)
- 755.5367 757.3368 758.8554 750.4179 3.6723
+ 754.8082 753.9005 756.9295 753.5945 1.5052
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.231 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.351 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 44bf2f52fe..411a45da87 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,217 +632,106 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [512], [])[cse_var_2] = 0f32
- compute_5[(cse_var_2 + 1)] = 0f32
- compute_5[(cse_var_2 + 2)] = 0f32
- compute_5[(cse_var_2 + 3)] = 0f32
- compute_5[(cse_var_2 + 4)] = 0f32
- compute_5[(cse_var_2 + 5)] = 0f32
- compute_5[(cse_var_2 + 6)] = 0f32
- compute_5[(cse_var_2 + 7)] = 0f32
- compute_5[(cse_var_2 + 8)] = 0f32
- compute_5[(cse_var_2 + 9)] = 0f32
- compute_5[(cse_var_2 + 10)] = 0f32
- compute_5[(cse_var_2 + 11)] = 0f32
- compute_5[(cse_var_2 + 12)] = 0f32
- compute_5[(cse_var_2 + 13)] = 0f32
- compute_5[(cse_var_2 + 14)] = 0f32
- compute_5[(cse_var_2 + 15)] = 0f32
- compute_5[(cse_var_2 + 32)] = 0f32
- compute_5[(cse_var_2 + 33)] = 0f32
- compute_5[(cse_var_2 + 34)] = 0f32
- compute_5[(cse_var_2 + 35)] = 0f32
- compute_5[(cse_var_2 + 36)] = 0f32
- compute_5[(cse_var_2 + 37)] = 0f32
- compute_5[(cse_var_2 + 38)] = 0f32
- compute_5[(cse_var_2 + 39)] = 0f32
- compute_5[(cse_var_2 + 40)] = 0f32
- compute_5[(cse_var_2 + 41)] = 0f32
- compute_5[(cse_var_2 + 42)] = 0f32
- compute_5[(cse_var_2 + 43)] = 0f32
- compute_5[(cse_var_2 + 44)] = 0f32
- compute_5[(cse_var_2 + 45)] = 0f32
- compute_5[(cse_var_2 + 46)] = 0f32
- compute_5[(cse_var_2 + 47)] = 0f32
- compute_5[(cse_var_2 + 64)] = 0f32
- compute_5[(cse_var_2 + 65)] = 0f32
- compute_5[(cse_var_2 + 66)] = 0f32
- compute_5[(cse_var_2 + 67)] = 0f32
- compute_5[(cse_var_2 + 68)] = 0f32
- compute_5[(cse_var_2 + 69)] = 0f32
- compute_5[(cse_var_2 + 70)] = 0f32
- compute_5[(cse_var_2 + 71)] = 0f32
- compute_5[(cse_var_2 + 72)] = 0f32
- compute_5[(cse_var_2 + 73)] = 0f32
- compute_5[(cse_var_2 + 74)] = 0f32
- compute_5[(cse_var_2 + 75)] = 0f32
- compute_5[(cse_var_2 + 76)] = 0f32
- compute_5[(cse_var_2 + 77)] = 0f32
- compute_5[(cse_var_2 + 78)] = 0f32
- compute_5[(cse_var_2 + 79)] = 0f32
- compute_5[(cse_var_2 + 96)] = 0f32
- compute_5[(cse_var_2 + 97)] = 0f32
- compute_5[(cse_var_2 + 98)] = 0f32
- compute_5[(cse_var_2 + 99)] = 0f32
- compute_5[(cse_var_2 + 100)] = 0f32
- compute_5[(cse_var_2 + 101)] = 0f32
- compute_5[(cse_var_2 + 102)] = 0f32
- compute_5[(cse_var_2 + 103)] = 0f32
- compute_5[(cse_var_2 + 104)] = 0f32
- compute_5[(cse_var_2 + 105)] = 0f32
- compute_5[(cse_var_2 + 106)] = 0f32
- compute_5[(cse_var_2 + 107)] = 0f32
- compute_5[(cse_var_2 + 108)] = 0f32
- compute_5[(cse_var_2 + 109)] = 0f32
- compute_5[(cse_var_2 + 110)] = 0f32
- compute_5[(cse_var_2 + 111)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- let cse_var_67: int32 = (elem_idx*16)
- let cse_var_66: int32 = (cse_var_2 + 99)
- let cse_var_65: int32 = (cse_var_2 + 98)
- let cse_var_64: int32 = (cse_var_2 + 97)
- let cse_var_63: int32 = (cse_var_2 + 96)
- let cse_var_62: int32 = (cse_var_2 + 9)
- let cse_var_61: int32 = (cse_var_2 + 8)
- let cse_var_60: int32 = (cse_var_2 + 79)
- let cse_var_59: int32 = (cse_var_2 + 78)
- let cse_var_58: int32 = (cse_var_2 + 77)
- let cse_var_57: int32 = (cse_var_2 + 76)
- let cse_var_56: int32 = (cse_var_2 + 75)
- let cse_var_55: int32 = (cse_var_2 + 74)
- let cse_var_54: int32 = (cse_var_2 + 73)
- let cse_var_53: int32 = (cse_var_2 + 72)
- let cse_var_52: int32 = (cse_var_2 + 71)
- let cse_var_51: int32 = (cse_var_2 + 70)
- let cse_var_50: int32 = (cse_var_2 + 7)
- let cse_var_49: int32 = (cse_var_2 + 69)
- let cse_var_48: int32 = (cse_var_2 + 68)
- let cse_var_47: int32 = (cse_var_2 + 67)
- let cse_var_46: int32 = (cse_var_2 + 66)
- let cse_var_45: int32 = (cse_var_2 + 65)
- let cse_var_44: int32 = (cse_var_2 + 64)
- let cse_var_43: int32 = (cse_var_2 + 6)
- let cse_var_42: int32 = (cse_var_2 + 5)
- let cse_var_41: int32 = (cse_var_2 + 47)
- let cse_var_40: int32 = (cse_var_2 + 46)
- let cse_var_39: int32 = (cse_var_2 + 45)
- let cse_var_38: int32 = (cse_var_2 + 44)
- let cse_var_37: int32 = (cse_var_2 + 43)
- let cse_var_36: int32 = (cse_var_2 + 42)
- let cse_var_35: int32 = (cse_var_2 + 41)
- let cse_var_34: int32 = (cse_var_2 + 40)
- let cse_var_33: int32 = (cse_var_2 + 4)
- let cse_var_32: int32 = (cse_var_2 + 39)
- let cse_var_31: int32 = (cse_var_2 + 38)
- let cse_var_30: int32 = (cse_var_2 + 37)
- let cse_var_29: int32 = (cse_var_2 + 36)
- let cse_var_28: int32 = (cse_var_2 + 35)
- let cse_var_27: int32 = (cse_var_2 + 34)
- let cse_var_26: int32 = (cse_var_2 + 33)
- let cse_var_25: int32 = (cse_var_2 + 32)
- let cse_var_24: int32 = (cse_var_2 + 3)
- let cse_var_23: int32 = (cse_var_2 + 2)
- let cse_var_22: int32 = (cse_var_2 + 15)
- let cse_var_21: int32 = (cse_var_2 + 14)
- let cse_var_20: int32 = (cse_var_2 + 13)
- let cse_var_19: int32 = (cse_var_2 + 12)
- let cse_var_18: int32 = (cse_var_2 + 111)
- let cse_var_17: int32 = (cse_var_2 + 110)
- let cse_var_16: int32 = (cse_var_2 + 11)
- let cse_var_15: int32 = (cse_var_2 + 109)
- let cse_var_14: int32 = (cse_var_2 + 108)
- let cse_var_13: int32 = (cse_var_2 + 107)
- let cse_var_12: int32 = (cse_var_2 + 106)
- let cse_var_11: int32 = (cse_var_2 + 105)
- let cse_var_10: int32 = (cse_var_2 + 104)
- let cse_var_9: int32 = (cse_var_2 + 103)
- let cse_var_8: int32 = (cse_var_2 + 102)
- let cse_var_7: int32 = (cse_var_2 + 101)
- let cse_var_6: int32 = (cse_var_2 + 100)
- let cse_var_5: int32 = (cse_var_2 + 10)
- let cse_var_4: int32 = (cse_var_2 + 1)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*1024))
- {
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_67)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_67)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_67) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 32) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ {
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = ((i.outer.inner*512) + (i.inner*16))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*8192)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_68: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_68, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -880,7 +769,7 @@ 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: 3.042 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.021 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 fea9ef5cf2..3fbc04784b 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>00:31.072</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:32.939</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:31.037</p></td>
+<td><p>00:32.904</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>
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 397eb164f5..810a4d345b 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,8 +567,26 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 17.24/17.24 result: MeasureResult(costs=(0.013425095444444445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.040456771850586, timestamp=1667929722.8924406) [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6074367
-No: 2 GFLOPS: 0.00/17.24 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 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, 2, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4046349
+No: 2 GFLOPS: 273.34/273.34 result: MeasureResult(costs=(0.0008469235,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.00227689743042, timestamp=1667930513.777336) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1764867
+No: 3 GFLOPS: 0.00/273.34 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
@@ -690,8 +708,8 @@ 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, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9636837
-No: 3 GFLOPS: 0.00/17.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4988951
+No: 4 GFLOPS: 0.00/273.34 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
@@ -813,9 +831,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2486608
-No: 4 GFLOPS: 3.69/17.24 result: MeasureResult(costs=(0.0628082655,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.670874834060669, timestamp=1667929724.9528527) [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5517272
-No: 5 GFLOPS: 0.00/17.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8220121
+No: 5 GFLOPS: 0.00/273.34 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
@@ -937,8 +954,8 @@ 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, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5788005
-No: 6 GFLOPS: 0.00/17.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1098987
+No: 6 GFLOPS: 0.00/273.34 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
@@ -1060,8 +1077,8 @@ 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, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3651387
-No: 7 GFLOPS: 0.00/17.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5468477
+No: 7 GFLOPS: 0.00/273.34 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
@@ -1183,9 +1200,8 @@ 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, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8161895
-No: 8 GFLOPS: 91.85/91.85 result: MeasureResult(costs=(0.0025205581860465115,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4904000759124756, timestamp=1667929728.4538808) [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3101383
-No: 9 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4711036
+No: 8 GFLOPS: 0.00/273.34 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
@@ -1307,8 +1323,8 @@ 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, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,379665
-No: 10 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3919317
+No: 9 GFLOPS: 0.00/273.34 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
@@ -1430,8 +1446,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8672709
-No: 11 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9480179
+No: 10 GFLOPS: 0.00/273.34 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
@@ -1553,8 +1569,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1044097
-No: 12 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4131591
+No: 11 GFLOPS: 0.00/273.34 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
@@ -1676,8 +1692,8 @@ 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, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,644049
-No: 13 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6324935
+No: 12 GFLOPS: 0.00/273.34 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
@@ -1799,9 +1815,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9275568
-No: 14 GFLOPS: 0.87/91.85 result: MeasureResult(costs=(0.26746337875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.2179131507873535, timestamp=1667929734.0918875) [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,247665
-No: 15 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1694286
+No: 13 GFLOPS: 0.00/273.34 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
@@ -1923,8 +1938,8 @@ 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, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1262849
-No: 16 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6253237
+No: 14 GFLOPS: 0.00/273.34 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
@@ -2046,8 +2061,9 @@ 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, 4, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8850976
-No: 17 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7223233
+No: 15 GFLOPS: 152.68/273.34 result: MeasureResult(costs=(0.0015162880138888887,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6183815002441406, timestamp=1667930519.9783366) [('tile_f', [-1, 1, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7014435
+No: 16 GFLOPS: 0.00/273.34 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
@@ -2169,8 +2185,8 @@ 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, 2, 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', 1500), ('unroll_explicit', 1)],None,10065585
-No: 18 GFLOPS: 0.00/91.85 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, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3928914
+No: 17 GFLOPS: 0.00/273.34 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
@@ -2292,8 +2308,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2437712
-No: 19 GFLOPS: 0.00/91.85 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7004638
+No: 18 GFLOPS: 0.00/273.34 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
@@ -2415,8 +2431,131 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9454711
-No: 20 GFLOPS: 3.97/91.85 result: MeasureResult(costs=(0.058333782,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9448578357696533, timestamp=1667929737.288313) [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3680068
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3410216
+No: 19 GFLOPS: 154.11/273.34 result: MeasureResult(costs=(0.001502168328358209,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4731054306030273, timestamp=1667930521.6758177) [('tile_f', [-1, 1, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3004604
+No: 20 GFLOPS: 0.00/273.34 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, 128, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10083367
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2455,9 +2594,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3101383
+[('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1764867
Finish loading 20 records
-Time cost of this operator: 0.001876
+Time cost of this operator: 0.001088
</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 1f7a60d6ee..3506126b13 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -595,10 +595,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.1 98.715 (1, 2, 10, 10, 3) 2 1 [311.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.973 (1, 6, 10, 10) 1 1 [3.066]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.986 0.313 (1, 1, 10, 10, 3) 1 1 [0.986]
-Total_time - 315.151 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.5 98.735 (1, 2, 10, 10, 3) 2 1 [312.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.045 0.962 (1, 6, 10, 10) 1 1 [3.045]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.959 0.303 (1, 1, 10, 10, 3) 1 1 [0.959]
+Total_time - 316.504 - - - - -
</pre></div>
</div>
</div>
@@ -649,10 +649,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.9 97.986 (1, 6, 10, 10, 1) 2 1 [134.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.809 1.314 (1, 6, 10, 10) 1 1 [1.809]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.7 (1, 1, 10, 10, 3) 1 1 [0.964]
-Total_time - 137.673 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.4 97.396 (1, 6, 10, 10, 1) 2 1 [102.4]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.771 1.684 (1, 6, 10, 10) 1 1 [1.771]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 0.919 (1, 1, 10, 10, 3) 1 1 [0.967]
+Total_time - 105.138 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index cb1957fb3d..b756e56d7a 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -529,7 +529,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp9l3zdfow/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpdvy0vmfd/images/random'
</pre></div>
</div>
</div>
@@ -589,8 +589,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[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], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp9l3zdfow/images/target contains 8144 images
-/tmp/tmp9l3zdfow/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpdvy0vmfd/images/target contains 8144 images
+/tmp/tmpdvy0vmfd/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -702,13 +702,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 46s - loss: 0.2186 - accuracy: 0.9260 - val_loss: 0.1653 - val_accuracy: 0.9517 - 46s/epoch - 142ms/step
+328/328 - 46s - loss: 0.2163 - accuracy: 0.9264 - val_loss: 0.1278 - val_accuracy: 0.9619 - 46s/epoch - 142ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0979 - accuracy: 0.9619 - val_loss: 0.1414 - val_accuracy: 0.9524 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0935 - accuracy: 0.9658 - val_loss: 0.1236 - val_accuracy: 0.9603 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0731 - accuracy: 0.9716 - val_loss: 0.1817 - val_accuracy: 0.9471 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0706 - accuracy: 0.9722 - val_loss: 0.1269 - val_accuracy: 0.9637 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f5fbe251d50>
+<keras.callbacks.History object at 0x7fde58700c90>
</pre></div>
</div>
</div>
@@ -970,7 +970,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 0.565 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 19.574 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 bcbe710408..2ca3524d61 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>05:01.578</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:19.873</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:00.565</p></td>
+<td><p>04:19.574</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:49.303</p></td>
+<td><p>00:48.919</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.027</p></td>
+<td><p>00:07.656</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.681</p></td>
+<td><p>00:03.722</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 e6ab2605da..901879dde7 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>00:43.246</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.004</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>00:31.529</p></td>
+<td><p>00:32.054</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>00:10.169</p></td>
+<td><p>00:10.251</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>00:01.541</p></td>
+<td><p>00:01.692</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 29ac0c93b1..61fbc2eb3a 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 0x7f5f5e3f0c20>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fde0207b5f0>
</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 30b369c59b..1689b04e15 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>00:06.210</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.738</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,31 +349,31 @@
</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>00:03.881</p></td>
+<td><p>00:03.410</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>00:01.030</p></td>
+<td><p>00:01.005</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>00:00.554</p></td>
+<td><p>00:00.566</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>00:00.537</p></td>
+<td><p>00:00.545</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>
-<td><p>00:00.048</p></td>
+<td><p>00:00.049</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.029</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index dfe8e2fbe5..6f4e1155ac 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/tmpuvwaf5gp/input0.cc'\nsource_filename = \"/tmp/tmpuvwaf5gp/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/tmpfclfy8je/input0.cc'\nsource_filename = \"/tmp/tmpfclfy8je/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 1ef28de467..23d2181e9d 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,7 +229,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index ff960976ba..385f57ffde 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 7c833b454b..7ecfc019bb 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/e43841d2e/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 20d0e732ec..9925e52ab2 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/e43841d2e/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 3ad5733eaa..6fc916a843 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/e43841d2e/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 4465a8af1e..939d8acd13 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/e43841d2e/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 8e192fb4e8..cd4efdde9f 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/e43841d2e/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 df46b4048b..cea40a0003 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/e43841d2e/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 ed997c510b..9fd5873e39 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/e43841d2e/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 aac89d10fb..28815ff9e8 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/e43841d2e/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 e08a1d433c..fb51a4c748 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/e43841d2e/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 25c3b9f1b9..bae8af5abd 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/e43841d2e/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 b253d92843..1f96f1dac9 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/e43841d2e/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 15ab1544bb..f66cb31ac8 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/e43841d2e/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 6d55a96be5..9d0fb63284 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/e43841d2e/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 085eb9fbc1..442a453ef1 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/e43841d2e/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 a964e2eacc..72c1c4dd13 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/e43841d2e/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 53fa72400d..0d566a48be 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/e43841d2e/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 2a44e253da..0307f4805c 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/e43841d2e/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 6940dc6976..b1f86600e2 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/e43841d2e/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 b390a05c4a..430e0cd8d1 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/e43841d2e/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 e56e07d622..925dc3289f 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/e43841d2e/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 7b620a1e80..c0e3e559c3 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/e43841d2e/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 77fc810e52..cf3c105d2d 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/e43841d2e/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 6c900e5f57..124f54dff5 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/e43841d2e/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 433599b3b8..6c93b781cd 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/e43841d2e/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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/e43841d2e/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be3023894/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 3bafbd27c5..efc2fed2ac 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 3de1ec9639..31e09f1bc0 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>00:26.453</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:26.251</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>00:26.447</p></td>
+<td><p>00:26.244</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 c693058f23..6fd0517e09 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 29.71s!
+resnet18_v1 inference graph built in 29.85s!
</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 0cc6df287a..f374b56453 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 19.77s!
+yolov3-tiny inference graph built in 20.14s!
</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 4635c65624..c3a9e6cebe 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>01:40.819</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:41.408</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>00:51.309</p></td>
+<td><p>00:51.590</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:49.510</p></td>
+<td><p>00:49.818</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 383aa1aad1..513fb2b91c 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>00:03.116</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.121</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>00:02.684</p></td>
+<td><p>00:02.673</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>00:00.433</p></td>
+<td><p>00:00.449</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 ae0617dde7..1e3d4a54a2 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>00:00.784</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.785</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>00:00.415</p></td>
+<td><p>00:00.418</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>00:00.369</p></td>
+<td><p>00:00.367</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 3f81f61b2a..733935a503 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,9 +491,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
-</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>
@@ -581,7 +578,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 97.901 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.309 ms
</pre></div>
</div>
</div>
@@ -645,7 +642,6 @@ 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>
@@ -656,7 +652,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.374 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.380 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 e0809aa5ec..edb2dac705 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: 10.94/10.94 result: MeasureResult(costs=(0.0245441248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6051483154296875, timestamp=1667928363.5591667) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
-No: 2 GFLOPS: 0.50/10.94 result: MeasureResult(costs=(0.5351993628,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.729020833969116, timestamp=1667928372.3072314) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
-No: 3 GFLOPS: 12.87/12.87 result: MeasureResult(costs=(0.020857743199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5411012172698975, timestamp=1667928373.5491374) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
-No: 4 GFLOPS: 0.90/12.87 result: MeasureResult(costs=(0.2995044662,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.939200162887573, timestamp=1667928378.5030456) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
-No: 5 GFLOPS: 2.16/12.87 result: MeasureResult(costs=(0.12419423380000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1458237171173096, timestamp=1667928380.7700942) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
-No: 6 GFLOPS: 3.03/12.87 result: MeasureResult(costs=(0.08850243220000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5829555988311768, timestamp=1667928383.118172) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
-No: 7 GFLOPS: 1.46/12.87 result: MeasureResult(costs=(0.183464197,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.087735414505005, timestamp=1667928386.9748073) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 8 GFLOPS: 12.03/12.87 result: MeasureResult(costs=(0.022319072000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5626184940338135, timestamp=1667928387.5537179) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
-No: 9 GFLOPS: 1.54/12.87 result: MeasureResult(costs=(0.1743451912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.924138069152832, timestamp=1667928390.8104784) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
-No: 10 GFLOPS: 9.74/12.87 result: MeasureResult(costs=(0.027557288999999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8015899658203125, timestamp=1667928391.4209356) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+No: 1 GFLOPS: 3.31/3.31 result: MeasureResult(costs=(0.0810645858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4697649478912354, timestamp=1667929171.7026908) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
+No: 2 GFLOPS: 13.36/13.36 result: MeasureResult(costs=(0.0200879916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5213887691497803, timestamp=1667929172.949474) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
+No: 3 GFLOPS: 3.15/13.36 result: MeasureResult(costs=(0.08508645540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.513859748840332, timestamp=1667929175.2222762) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
+No: 4 GFLOPS: 9.82/13.36 result: MeasureResult(costs=(0.0273386124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5807535648345947, timestamp=1667929175.8264558) [('tile_y', [-1, 2]), ('tile_x', [-1, 32])],None,51
+No: 5 GFLOPS: 12.47/13.36 result: MeasureResult(costs=(0.0215216234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5087535381317139, timestamp=1667929176.4627697) [('tile_y', [-1, 128]), ('tile_x', [-1, 256])],None,87
+No: 6 GFLOPS: 0.46/13.36 result: MeasureResult(costs=(0.5822482323999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.480411529541016, timestamp=1667929185.9742908) [('tile_y', [-1, 512]), ('tile_x', [-1, 1])],None,9
+No: 7 GFLOPS: 10.23/13.36 result: MeasureResult(costs=(0.0262322748,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5583615303039551, timestamp=1667929187.3201284) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+No: 8 GFLOPS: 0.90/13.36 result: MeasureResult(costs=(0.2995719126,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.9787445068359375, timestamp=1667929192.317788) [('tile_y', [-1, 128]), ('tile_x', [-1, 2])],None,17
+No: 9 GFLOPS: 1.76/13.36 result: MeasureResult(costs=(0.1526136742,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.569279909133911, timestamp=1667929195.0051718) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+No: 10 GFLOPS: 3.55/13.36 result: MeasureResult(costs=(0.07568241719999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3339037895202637, timestamp=1667929196.3810997) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
</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 122aa53e9b..bc3e9f0e28 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': 516.4690437500008, 'median': 516.2654152999949, 'std': 1.9471380053512977}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 523.8234768699988, 'median': 524.8220038499994, 'std': 3.2826715339377572}
</pre></div>
</div>
</div>
@@ -712,177 +712,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 21.77/ 21.77 GFLOPS | Progress: (4/20) | 6.93 s
-[Task 1/25] Current/Best: 18.85/ 21.77 GFLOPS | Progress: (8/20) | 11.39 s
-[Task 1/25] Current/Best: 9.94/ 21.77 GFLOPS | Progress: (12/20) | 13.82 s
-[Task 1/25] Current/Best: 23.22/ 23.22 GFLOPS | Progress: (16/20) | 16.47 s
-[Task 1/25] Current/Best: 18.93/ 23.22 GFLOPS | Progress: (20/20) | 19.99 s Done.
+[Task 1/25] Current/Best: 12.75/ 19.42 GFLOPS | Progress: (4/20) | 7.82 s
+[Task 1/25] Current/Best: 23.65/ 23.65 GFLOPS | Progress: (8/20) | 11.06 s
+[Task 1/25] Current/Best: 17.85/ 23.65 GFLOPS | Progress: (12/20) | 13.43 s
+[Task 1/25] Current/Best: 13.52/ 23.65 GFLOPS | Progress: (16/20) | 16.13 s
+[Task 1/25] Current/Best: 12.43/ 23.65 GFLOPS | Progress: (20/20) | 21.61 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 6.43/ 22.67 GFLOPS | Progress: (4/20) | 2.83 s
-[Task 2/25] Current/Best: 19.22/ 22.67 GFLOPS | Progress: (8/20) | 3.83 s
-[Task 2/25] Current/Best: 7.90/ 22.67 GFLOPS | Progress: (12/20) | 5.01 s
-[Task 2/25] Current/Best: 8.63/ 22.67 GFLOPS | Progress: (16/20) | 6.64 s
-[Task 2/25] Current/Best: 8.51/ 22.67 GFLOPS | Progress: (20/20) | 8.03 s Done.
+[Task 2/25] Current/Best: 8.03/ 21.41 GFLOPS | Progress: (4/20) | 2.52 s
+[Task 2/25] Current/Best: 14.39/ 21.41 GFLOPS | Progress: (8/20) | 3.59 s
+[Task 2/25] Current/Best: 15.81/ 23.06 GFLOPS | Progress: (12/20) | 4.86 s
+[Task 2/25] Current/Best: 12.58/ 23.06 GFLOPS | Progress: (16/20) | 6.33 s
+[Task 2/25] Current/Best: 8.29/ 23.06 GFLOPS | Progress: (20/20) | 8.30 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 14.73/ 14.73 GFLOPS | Progress: (4/20) | 3.91 s
-[Task 3/25] Current/Best: 23.98/ 23.98 GFLOPS | Progress: (8/20) | 5.48 s
-[Task 3/25] Current/Best: 12.58/ 23.98 GFLOPS | Progress: (12/20) | 7.54 s
-[Task 3/25] Current/Best: 6.17/ 23.98 GFLOPS | Progress: (16/20) | 9.53 s
-[Task 3/25] Current/Best: 16.37/ 23.98 GFLOPS | Progress: (20/20) | 11.48 s Done.
+[Task 3/25] Current/Best: 6.77/ 23.89 GFLOPS | Progress: (4/20) | 3.45 s
+[Task 3/25] Current/Best: 19.40/ 23.89 GFLOPS | Progress: (8/20) | 5.31 s
+[Task 3/25] Current/Best: 15.54/ 23.89 GFLOPS | Progress: (12/20) | 7.27 s
+[Task 3/25] Current/Best: 5.61/ 23.89 GFLOPS | Progress: (16/20) | 10.66 s
+[Task 3/25] Current/Best: 5.28/ 23.89 GFLOPS | Progress: (20/20) | 14.99 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 12.06/ 13.87 GFLOPS | Progress: (4/20) | 3.92 s
-[Task 4/25] Current/Best: 15.04/ 22.48 GFLOPS | Progress: (8/20) | 5.31 s
-[Task 4/25] Current/Best: 9.76/ 22.48 GFLOPS | Progress: (12/20) | 6.96 s
-[Task 4/25] Current/Best: 21.42/ 22.48 GFLOPS | Progress: (16/20) | 8.77 s
-[Task 4/25] Current/Best: 18.81/ 22.48 GFLOPS | Progress: (20/20) | 13.65 s Done.
+[Task 4/25] Current/Best: 11.40/ 18.76 GFLOPS | Progress: (4/20) | 3.05 s
+[Task 4/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (8/20) | 6.99 s
+[Task 4/25] Current/Best: 6.19/ 19.99 GFLOPS | Progress: (12/20) | 12.20 s
+[Task 4/25] Current/Best: 16.57/ 20.19 GFLOPS | Progress: (16/20) | 18.44 s
+[Task 4/25] Current/Best: 12.37/ 20.19 GFLOPS | Progress: (20/20) | 20.20 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 13.14/ 13.14 GFLOPS | Progress: (4/20) | 3.29 s
-[Task 5/25] Current/Best: 13.48/ 15.01 GFLOPS | Progress: (8/20) | 5.10 s
-[Task 5/25] Current/Best: 8.39/ 17.15 GFLOPS | Progress: (12/20) | 7.20 s
-[Task 5/25] Current/Best: 9.74/ 17.15 GFLOPS | Progress: (16/20) | 9.57 s
-[Task 5/25] Current/Best: 13.37/ 17.15 GFLOPS | Progress: (20/20) | 11.52 s Done.
+[Task 5/25] Current/Best: 5.63/ 20.55 GFLOPS | Progress: (4/20) | 3.57 s
+[Task 5/25] Current/Best: 3.92/ 20.98 GFLOPS | Progress: (8/20) | 5.37 s
+[Task 5/25] Current/Best: 15.45/ 20.98 GFLOPS | Progress: (12/20) | 7.13 s
+[Task 5/25] Current/Best: 13.93/ 20.98 GFLOPS | Progress: (16/20) | 9.19 s
+[Task 5/25] Current/Best: 12.76/ 20.98 GFLOPS | Progress: (20/20) | 12.68 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 15.76/ 15.76 GFLOPS | Progress: (4/20) | 5.09 s
-[Task 6/25] Current/Best: 16.57/ 16.57 GFLOPS | Progress: (8/20) | 7.51 s
-[Task 6/25] Current/Best: 11.83/ 16.57 GFLOPS | Progress: (12/20) | 9.44 s
-[Task 6/25] Current/Best: 14.53/ 16.57 GFLOPS | Progress: (16/20) | 12.12 s
-[Task 6/25] Current/Best: 13.67/ 16.57 GFLOPS | Progress: (20/20) | 14.69 s Done.
+[Task 6/25] Current/Best: 18.87/ 18.87 GFLOPS | Progress: (4/20) | 3.94 s
+[Task 6/25] Current/Best: 7.03/ 18.87 GFLOPS | Progress: (8/20) | 6.44 s
+[Task 6/25] Current/Best: 11.09/ 18.87 GFLOPS | Progress: (12/20) | 10.86 s
+[Task 6/25] Current/Best: 13.13/ 18.87 GFLOPS | Progress: (16/20) | 13.36 s
+[Task 6/25] Current/Best: 14.36/ 18.87 GFLOPS | Progress: (20/20) | 15.44 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 14.55/ 14.55 GFLOPS | Progress: (4/20) | 3.69 s
-[Task 7/25] Current/Best: 18.33/ 18.33 GFLOPS | Progress: (8/20) | 5.69 s
-[Task 7/25] Current/Best: 10.15/ 19.33 GFLOPS | Progress: (12/20) | 7.76 s
-[Task 7/25] Current/Best: 16.76/ 19.33 GFLOPS | Progress: (16/20) | 10.56 s
-[Task 7/25] Current/Best: 8.06/ 19.33 GFLOPS | Progress: (20/20) | 13.82 s Done.
+[Task 7/25] Current/Best: 4.90/ 11.86 GFLOPS | Progress: (4/20) | 3.81 s
+[Task 7/25] Current/Best: 17.84/ 18.32 GFLOPS | Progress: (8/20) | 7.05 s
+[Task 7/25] Current/Best: 6.30/ 18.32 GFLOPS | Progress: (12/20) | 9.72 s
+[Task 7/25] Current/Best: 11.72/ 18.32 GFLOPS | Progress: (16/20) | 12.15 s
+[Task 7/25] Current/Best: 18.74/ 19.94 GFLOPS | Progress: (20/20) | 14.17 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 2.41/ 14.02 GFLOPS | Progress: (4/20) | 13.64 s
-[Task 8/25] Current/Best: 6.81/ 17.39 GFLOPS | Progress: (8/20) | 16.40 s
-[Task 8/25] Current/Best: 12.27/ 17.39 GFLOPS | Progress: (12/20) | 28.09 s
-[Task 8/25] Current/Best: 8.38/ 17.39 GFLOPS | Progress: (16/20) | 30.65 s
-[Task 8/25] Current/Best: 21.76/ 21.76 GFLOPS | Progress: (20/20) | 32.93 s
+[Task 8/25] Current/Best: 8.38/ 21.12 GFLOPS | Progress: (4/20) | 4.69 s
+[Task 8/25] Current/Best: 6.45/ 21.12 GFLOPS | Progress: (8/20) | 6.85 s
+[Task 8/25] Current/Best: 13.36/ 21.12 GFLOPS | Progress: (12/20) | 18.12 s
+[Task 8/25] Current/Best: 9.88/ 21.12 GFLOPS | Progress: (16/20) | 21.36 s
+[Task 8/25] Current/Best: 9.35/ 21.12 GFLOPS | Progress: (20/20) | 30.59 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 8.24/ 10.13 GFLOPS | Progress: (4/20) | 5.14 s
-[Task 9/25] Current/Best: 17.31/ 17.31 GFLOPS | Progress: (8/20) | 8.94 s
-[Task 9/25] Current/Best: 19.85/ 19.85 GFLOPS | Progress: (12/20) | 13.74 s
-[Task 9/25] Current/Best: 18.91/ 19.85 GFLOPS | Progress: (16/20) | 17.67 s
-[Task 9/25] Current/Best: 11.52/ 19.85 GFLOPS | Progress: (20/20) | 19.87 s Done.
+[Task 9/25] Current/Best: 16.46/ 16.46 GFLOPS | Progress: (4/20) | 2.94 s
+[Task 9/25] Current/Best: 8.15/ 19.55 GFLOPS | Progress: (8/20) | 6.51 s
+[Task 9/25] Current/Best: 17.08/ 19.55 GFLOPS | Progress: (12/20) | 8.01 s
+[Task 9/25] Current/Best: 18.65/ 19.55 GFLOPS | Progress: (16/20) | 9.62 s
+[Task 9/25] Current/Best: 6.10/ 22.73 GFLOPS | Progress: (20/20) | 18.32 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 10.23/ 19.06 GFLOPS | Progress: (4/20) | 3.13 s
-[Task 10/25] Current/Best: 17.85/ 19.06 GFLOPS | Progress: (8/20) | 4.60 s
-[Task 10/25] Current/Best: 10.66/ 19.06 GFLOPS | Progress: (12/20) | 6.38 s
-[Task 10/25] Current/Best: 3.82/ 19.06 GFLOPS | Progress: (16/20) | 8.05 s
-[Task 10/25] Current/Best: 10.08/ 19.06 GFLOPS | Progress: (20/20) | 11.79 s Done.
+[Task 10/25] Current/Best: 9.32/ 13.81 GFLOPS | Progress: (4/20) | 3.77 s
+[Task 10/25] Current/Best: 6.84/ 15.59 GFLOPS | Progress: (8/20) | 5.17 s
+[Task 10/25] Current/Best: 18.06/ 20.05 GFLOPS | Progress: (12/20) | 6.53 s
+[Task 10/25] Current/Best: 3.03/ 20.05 GFLOPS | Progress: (16/20) | 10.53 s
+[Task 10/25] Current/Best: 10.54/ 20.05 GFLOPS | Progress: (20/20) | 12.47 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 10.89/ 11.41 GFLOPS | Progress: (4/20) | 4.66 s
-[Task 11/25] Current/Best: 15.95/ 19.41 GFLOPS | Progress: (8/20) | 6.71 s
-[Task 11/25] Current/Best: 15.55/ 19.41 GFLOPS | Progress: (12/20) | 9.40 s
-[Task 11/25] Current/Best: 13.04/ 19.41 GFLOPS | Progress: (16/20) | 11.60 s
-[Task 11/25] Current/Best: 17.69/ 21.24 GFLOPS | Progress: (20/20) | 13.53 s Done.
+[Task 11/25] Current/Best: 10.93/ 12.31 GFLOPS | Progress: (4/20) | 4.06 s
+[Task 11/25] Current/Best: 19.26/ 23.28 GFLOPS | Progress: (8/20) | 6.13 s
+[Task 11/25] Current/Best: 1.59/ 23.28 GFLOPS | Progress: (12/20) | 9.87 s
+[Task 11/25] Current/Best: 22.20/ 23.28 GFLOPS | Progress: (16/20) | 11.89 s
+[Task 11/25] Current/Best: 15.61/ 23.28 GFLOPS | Progress: (20/20) | 14.15 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 18.59/ 21.28 GFLOPS | Progress: (4/20) | 3.15 s
-[Task 12/25] Current/Best: 21.53/ 21.53 GFLOPS | Progress: (8/20) | 5.11 s
-[Task 12/25] Current/Best: 10.03/ 21.53 GFLOPS | Progress: (12/20) | 7.35 s
-[Task 12/25] Current/Best: 7.09/ 21.53 GFLOPS | Progress: (16/20) | 9.58 s
-[Task 12/25] Current/Best: 8.17/ 21.53 GFLOPS | Progress: (20/20) | 14.22 s Done.
+[Task 12/25] Current/Best: 17.00/ 21.91 GFLOPS | Progress: (4/20) | 4.50 s
+[Task 12/25] Current/Best: 5.47/ 21.91 GFLOPS | Progress: (8/20) | 6.91 s
+[Task 12/25] Current/Best: 11.95/ 21.91 GFLOPS | Progress: (12/20) | 9.05 s
+[Task 12/25] Current/Best: 10.42/ 21.91 GFLOPS | Progress: (16/20) | 15.33 s
+[Task 12/25] Current/Best: 12.57/ 21.91 GFLOPS | Progress: (20/20) | 18.37 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 23.51/ 23.51 GFLOPS | Progress: (4/20) | 3.66 s
-[Task 13/25] Current/Best: 13.84/ 23.51 GFLOPS | Progress: (8/20) | 5.74 s
-[Task 13/25] Current/Best: 11.76/ 23.51 GFLOPS | Progress: (12/20) | 8.56 s
-[Task 13/25] Current/Best: 12.83/ 23.51 GFLOPS | Progress: (16/20) | 10.35 s
-[Task 13/25] Current/Best: 5.76/ 23.51 GFLOPS | Progress: (20/20) | 12.61 s Done.
+[Task 13/25] Current/Best: 20.60/ 20.60 GFLOPS | Progress: (4/20) | 4.41 s
+[Task 13/25] Current/Best: 18.65/ 20.60 GFLOPS | Progress: (8/20) | 7.04 s
+[Task 13/25] Current/Best: 3.11/ 20.60 GFLOPS | Progress: (12/20) | 10.36 s
+[Task 13/25] Current/Best: 1.57/ 20.60 GFLOPS | Progress: (16/20) | 15.42 s
+[Task 13/25] Current/Best: 13.28/ 20.60 GFLOPS | Progress: (20/20) | 17.50 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 15.67/ 15.67 GFLOPS | Progress: (4/20) | 3.43 s
-[Task 14/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (8/20) | 6.38 s
-[Task 14/25] Current/Best: 13.52/ 19.58 GFLOPS | Progress: (12/20) | 11.28 s
-[Task 14/25] Current/Best: 6.06/ 19.58 GFLOPS | Progress: (16/20) | 14.33 s
-[Task 14/25] Current/Best: 10.37/ 19.58 GFLOPS | Progress: (20/20) | 16.30 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 6.86/ 18.04 GFLOPS | Progress: (4/20) | 2.94 s Done.
- Done.
+[Task 14/25] Current/Best: 13.51/ 14.68 GFLOPS | Progress: (4/20) | 3.57 s
+[Task 14/25] Current/Best: 10.79/ 16.27 GFLOPS | Progress: (8/20) | 7.87 s Done.
-[Task 15/25] Current/Best: 19.11/ 20.16 GFLOPS | Progress: (8/20) | 4.28 s
-[Task 15/25] Current/Best: 10.53/ 20.16 GFLOPS | Progress: (12/20) | 9.33 s
-[Task 15/25] Current/Best: 13.04/ 22.15 GFLOPS | Progress: (16/20) | 10.81 s
-[Task 15/25] Current/Best: 16.38/ 22.15 GFLOPS | Progress: (20/20) | 12.31 s
+[Task 14/25] Current/Best: 10.90/ 17.41 GFLOPS | Progress: (12/20) | 9.87 s
+[Task 14/25] Current/Best: 10.68/ 17.41 GFLOPS | Progress: (16/20) | 14.37 s
+[Task 14/25] Current/Best: 16.08/ 17.41 GFLOPS | Progress: (20/20) | 16.50 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 15/25] Current/Best: 21.57/ 21.57 GFLOPS | Progress: (4/20) | 3.82 s
+[Task 15/25] Current/Best: 18.31/ 21.57 GFLOPS | Progress: (8/20) | 8.81 s
+[Task 15/25] Current/Best: 18.78/ 21.57 GFLOPS | Progress: (12/20) | 10.44 s
+[Task 15/25] Current/Best: 15.31/ 21.57 GFLOPS | Progress: (16/20) | 13.03 s
+[Task 15/25] Current/Best: 9.49/ 21.57 GFLOPS | Progress: (20/20) | 18.99 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 11.21/ 20.70 GFLOPS | Progress: (4/20) | 3.90 s
-[Task 16/25] Current/Best: 13.35/ 20.70 GFLOPS | Progress: (8/20) | 6.72 s
-[Task 16/25] Current/Best: 13.69/ 20.70 GFLOPS | Progress: (12/20) | 8.38 s
-[Task 16/25] Current/Best: 14.93/ 20.70 GFLOPS | Progress: (16/20) | 10.03 s
-[Task 16/25] Current/Best: 13.40/ 20.70 GFLOPS | Progress: (20/20) | 11.34 s Done.
+[Task 16/25] Current/Best: 12.30/ 17.84 GFLOPS | Progress: (4/20) | 2.94 s
+[Task 16/25] Current/Best: 14.71/ 17.84 GFLOPS | Progress: (8/20) | 4.33 s Done.
+
+[Task 16/25] Current/Best: 6.85/ 18.56 GFLOPS | Progress: (12/20) | 5.73 s
+[Task 16/25] Current/Best: 11.64/ 19.06 GFLOPS | Progress: (16/20) | 6.93 s
+[Task 16/25] Current/Best: 2.80/ 19.06 GFLOPS | Progress: (20/20) | 9.84 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 9.31/ 20.44 GFLOPS | Progress: (4/20) | 4.00 s
-[Task 17/25] Current/Best: 5.35/ 20.44 GFLOPS | Progress: (8/20) | 6.42 s
-[Task 17/25] Current/Best: 16.04/ 20.44 GFLOPS | Progress: (12/20) | 9.84 s
-[Task 17/25] Current/Best: 14.82/ 21.93 GFLOPS | Progress: (16/20) | 13.13 s
-[Task 17/25] Current/Best: 16.75/ 21.93 GFLOPS | Progress: (20/20) | 16.18 s Done.
+[Task 17/25] Current/Best: 11.03/ 20.50 GFLOPS | Progress: (4/20) | 3.52 s
+[Task 17/25] Current/Best: 8.99/ 20.50 GFLOPS | Progress: (8/20) | 8.04 s
+[Task 17/25] Current/Best: 10.01/ 20.50 GFLOPS | Progress: (12/20) | 10.34 s
+[Task 17/25] Current/Best: 16.23/ 21.30 GFLOPS | Progress: (16/20) | 13.78 s
+[Task 17/25] Current/Best: 16.46/ 21.30 GFLOPS | Progress: (20/20) | 17.34 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 14.83/ 18.19 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 18/25] Current/Best: 11.40/ 18.27 GFLOPS | Progress: (8/20) | 5.39 s
-[Task 18/25] Current/Best: 11.83/ 19.55 GFLOPS | Progress: (12/20) | 7.44 s
-[Task 18/25] Current/Best: 10.25/ 19.55 GFLOPS | Progress: (16/20) | 11.23 s
-[Task 18/25] Current/Best: 14.98/ 19.55 GFLOPS | Progress: (20/20) | 14.63 s Done.
+[Task 18/25] Current/Best: 11.59/ 20.41 GFLOPS | Progress: (4/20) | 3.44 s
+[Task 18/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (8/20) | 5.25 s
+[Task 18/25] Current/Best: 12.37/ 20.86 GFLOPS | Progress: (12/20) | 10.84 s
+[Task 18/25] Current/Best: 11.36/ 20.86 GFLOPS | Progress: (16/20) | 13.90 s
+[Task 18/25] Current/Best: 18.15/ 20.86 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: 12.05/ 18.99 GFLOPS | Progress: (4/20) | 4.62 s
-[Task 19/25] Current/Best: 19.00/ 21.84 GFLOPS | Progress: (8/20) | 6.66 s
-[Task 19/25] Current/Best: 10.30/ 21.84 GFLOPS | Progress: (12/20) | 10.46 s
-[Task 19/25] Current/Best: 8.99/ 21.84 GFLOPS | Progress: (16/20) | 13.86 s
-[Task 19/25] Current/Best: 18.17/ 21.84 GFLOPS | Progress: (20/20) | 16.46 s Done.
+[Task 19/25] Current/Best: 10.94/ 23.09 GFLOPS | Progress: (4/20) | 6.07 s
+[Task 19/25] Current/Best: 11.17/ 23.09 GFLOPS | Progress: (8/20) | 11.90 s
+[Task 19/25] Current/Best: 3.09/ 23.09 GFLOPS | Progress: (12/20) | 16.65 s
+[Task 19/25] Current/Best: 19.30/ 23.09 GFLOPS | Progress: (16/20) | 18.87 s
+[Task 19/25] Current/Best: 17.88/ 23.09 GFLOPS | Progress: (20/20) | 21.58 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 10.74/ 12.50 GFLOPS | Progress: (4/20) | 3.38 s
-[Task 20/25] Current/Best: 9.22/ 17.91 GFLOPS | Progress: (8/20) | 6.32 s
-[Task 20/25] Current/Best: 16.64/ 17.91 GFLOPS | Progress: (12/20) | 9.46 s
-[Task 20/25] Current/Best: 10.19/ 17.91 GFLOPS | Progress: (16/20) | 11.34 s
-[Task 20/25] Current/Best: 17.38/ 17.91 GFLOPS | Progress: (20/20) | 14.51 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+[Task 20/25] Current/Best: 10.56/ 13.09 GFLOPS | Progress: (4/20) | 3.70 s
+[Task 20/25] Current/Best: 5.21/ 18.07 GFLOPS | Progress: (8/20) | 7.52 s
+[Task 20/25] Current/Best: 11.68/ 18.07 GFLOPS | Progress: (12/20) | 9.33 s
+[Task 20/25] Current/Best: 14.19/ 21.56 GFLOPS | Progress: (16/20) | 11.76 s
+[Task 20/25] Current/Best: 7.37/ 21.56 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: 6.38/ 19.16 GFLOPS | Progress: (4/20) | 3.11 s
+[Task 21/25] Current/Best: 20.35/ 20.35 GFLOPS | Progress: (8/20) | 6.91 s
+[Task 21/25] Current/Best: 11.27/ 20.35 GFLOPS | Progress: (12/20) | 9.17 s
+[Task 21/25] Current/Best: 15.94/ 22.10 GFLOPS | Progress: (16/20) | 11.31 s
+[Task 21/25] Current/Best: 14.08/ 22.10 GFLOPS | Progress: (20/20) | 12.67 s
+[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 22/25] Current/Best: 13.06/ 13.06 GFLOPS | Progress: (4/20) | 3.97 s
+[Task 22/25] Current/Best: 10.64/ 20.54 GFLOPS | Progress: (8/20) | 5.72 s Done.
Done.
-[Task 21/25] Current/Best: 13.54/ 13.54 GFLOPS | Progress: (4/20) | 3.01 s
-[Task 21/25] Current/Best: 5.35/ 15.15 GFLOPS | Progress: (8/20) | 5.29 s
-[Task 21/25] Current/Best: 16.33/ 16.33 GFLOPS | Progress: (12/20) | 7.36 s
-[Task 21/25] Current/Best: 10.31/ 20.17 GFLOPS | Progress: (16/20) | 9.32 s
-[Task 21/25] Current/Best: 9.47/ 20.17 GFLOPS | Progress: (20/20) | 11.79 s
-[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 15.75/ 15.75 GFLOPS | Progress: (4/20) | 3.52 s
-[Task 22/25] Current/Best: 13.60/ 15.75 GFLOPS | Progress: (8/20) | 5.78 s
-[Task 22/25] Current/Best: 12.22/ 21.68 GFLOPS | Progress: (12/20) | 7.21 s
-[Task 22/25] Current/Best: 13.78/ 21.68 GFLOPS | Progress: (16/20) | 8.87 s
-[Task 22/25] Current/Best: 4.09/ 21.68 GFLOPS | Progress: (20/20) | 10.82 s Done.
+[Task 22/25] Current/Best: 14.00/ 20.54 GFLOPS | Progress: (12/20) | 8.01 s
+[Task 22/25] Current/Best: 10.78/ 20.54 GFLOPS | Progress: (16/20) | 10.76 s
+[Task 22/25] Current/Best: 5.26/ 20.54 GFLOPS | Progress: (20/20) | 13.11 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 6.16/ 18.39 GFLOPS | Progress: (4/20) | 5.81 s
-[Task 23/25] Current/Best: 17.80/ 22.51 GFLOPS | Progress: (8/20) | 7.90 s
-[Task 23/25] Current/Best: 12.43/ 22.79 GFLOPS | Progress: (12/20) | 11.19 s
-[Task 23/25] Current/Best: 12.77/ 22.79 GFLOPS | Progress: (16/20) | 14.36 s
-[Task 23/25] Current/Best: 12.25/ 22.79 GFLOPS | Progress: (20/20) | 17.54 s Done.
+[Task 23/25] Current/Best: 19.41/ 19.41 GFLOPS | Progress: (4/20) | 10.20 s
+[Task 23/25] Current/Best: 10.62/ 19.41 GFLOPS | Progress: (8/20) | 12.24 s
+[Task 23/25] Current/Best: 17.91/ 19.41 GFLOPS | Progress: (12/20) | 14.62 s
+[Task 23/25] Current/Best: 21.94/ 21.94 GFLOPS | Progress: (16/20) | 18.00 s
+[Task 23/25] Current/Best: 7.43/ 21.94 GFLOPS | Progress: (20/20) | 21.77 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 3.69/ 3.69 GFLOPS | Progress: (4/20) | 12.27 s
-[Task 24/25] Current/Best: 9.77/ 9.77 GFLOPS | Progress: (8/20) | 22.75 s
-[Task 24/25] Current/Best: 2.28/ 10.04 GFLOPS | Progress: (12/20) | 29.02 s
-[Task 24/25] Current/Best: 7.51/ 10.60 GFLOPS | Progress: (16/20) | 39.48 s
-[Task 24/25] Current/Best: 0.78/ 10.60 GFLOPS | Progress: (20/20) | 51.38 s
+[Task 24/25] Current/Best: 1.46/ 6.86 GFLOPS | Progress: (4/20) | 12.08 s
+[Task 24/25] Current/Best: 3.30/ 8.63 GFLOPS | Progress: (8/20) | 14.97 s
+[Task 24/25] Current/Best: 2.02/ 10.64 GFLOPS | Progress: (12/20) | 17.59 s
+[Task 24/25] Current/Best: 3.37/ 10.64 GFLOPS | Progress: (16/20) | 28.31 s
+[Task 24/25] Current/Best: 3.57/ 10.64 GFLOPS | Progress: (20/20) | 38.84 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 4.12/ 9.33 GFLOPS | Progress: (4/20) | 12.22 s
-[Task 25/25] Current/Best: 6.00/ 9.33 GFLOPS | Progress: (8/20) | 22.97 s
-[Task 25/25] Current/Best: 3.01/ 9.33 GFLOPS | Progress: (12/20) | 34.45 s
-[Task 25/25] Current/Best: 5.39/ 9.33 GFLOPS | Progress: (16/20) | 41.84 s
-[Task 25/25] Current/Best: 5.23/ 9.33 GFLOPS | Progress: (20/20) | 52.35 s
+[Task 25/25] Current/Best: 1.55/ 5.79 GFLOPS | Progress: (4/20) | 3.53 s Done.
+
+[Task 25/25] Current/Best: 8.48/ 8.48 GFLOPS | Progress: (8/20) | 14.01 s
+[Task 25/25] Current/Best: 1.55/ 8.48 GFLOPS | Progress: (12/20) | 16.15 s
+[Task 25/25] Current/Best: 9.04/ 9.04 GFLOPS | Progress: (16/20) | 26.64 s
+[Task 25/25] Current/Best: 5.31/ 9.04 GFLOPS | Progress: (20/20) | 38.16 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -943,8 +944,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -981,8 +982,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 415.02006364999716, 'median': 415.1313719999962, 'std': 2.8967793135913644}
-unoptimized: {'mean': 516.4690437500008, 'median': 516.2654152999949, 'std': 1.9471380053512977}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 414.4846720199962, 'median': 414.8631147499941, 'std': 1.3101257155342834}
+unoptimized: {'mean': 523.8234768699988, 'median': 524.8220038499994, 'std': 3.2826715339377572}
</pre></div>
</div>
</div>
@@ -996,7 +997,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 52.204 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 12.873 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 598842acc2..a7426b6a5c 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>1.432e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.228e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 903c6a4b08..7dca245453 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>
... 225 lines suppressed ...